BestHub
Sign in
Tagged articles

AI research

312 articles · Page 2 of 4
Kuaishou Tech
Kuaishou Tech
Nov 25, 2025 · Artificial Intelligence

How Flow‑GRPO Boosts Image Generation Accuracy to 95% with Online Reinforcement Learning

Flow‑GRPO introduces online reinforcement learning into flow‑matching models by converting deterministic ODE sampling to stochastic SDE sampling and reducing denoising steps, raising SD‑3.5‑Medium's GenEval accuracy from 63% to 95%—surpassing GPT‑4o—and demonstrating strong gains in complex composition, text rendering, and human‑preference alignment across multiple generative tasks.

AI researchFlow Matchingdeep learning
0 likes · 8 min read
How Flow‑GRPO Boosts Image Generation Accuracy to 95% with Online Reinforcement Learning
HyperAI Super Neural
HyperAI Super Neural
Nov 19, 2025 · Artificial Intelligence

LocDiff: Achieving Global-Scale Precise Image Geolocation Without Grids or Reference Libraries

The LocDiff framework introduces a spherical‑harmonics Dirac‑delta encoding and a conditional Siren‑UNet diffusion model that enables accurate worldwide image geolocation without relying on predefined grids or external image libraries, outperforming prior methods in precision, generalization, and computational efficiency.

AI researchLocDiffdiffusion models
0 likes · 16 min read
LocDiff: Achieving Global-Scale Precise Image Geolocation Without Grids or Reference Libraries
Data Party THU
Data Party THU
Nov 13, 2025 · Artificial Intelligence

What Makes the Free Transformer a Game‑Changer in AI Decoding?

The Free Transformer paper introduces a decoder architecture that injects random latent variables to condition generation, breaking traditional GPT constraints and achieving notable performance gains on reasoning‑heavy benchmarks such as HumanEval+, MBPP, GSM8K, MMLU, and CSQA.

AI researchFree TransformerTransformer
0 likes · 10 min read
What Makes the Free Transformer a Game‑Changer in AI Decoding?
Alimama Tech
Alimama Tech
Nov 11, 2025 · Artificial Intelligence

Industrial-Scale Graph Learning: Boosting Ad ROI and Winning Beijing’s Science Award

The award‑winning industrial graph learning system developed by Peking University and Alibaba Mama combines novel dynamic graph embedding and GNN techniques, scales to millions of merchants, and has driven over 12% ad ROI improvement while publishing dozens of top‑conference papers.

AI researchadvertising optimizationgraph learning
0 likes · 6 min read
Industrial-Scale Graph Learning: Boosting Ad ROI and Winning Beijing’s Science Award
Data Party THU
Data Party THU
Nov 5, 2025 · Artificial Intelligence

How VLM‑FO1 Turns Vision‑Language Models into Precise Perception Machines

VLM‑FO1 introduces a generate‑plus‑reference paradigm that replaces coordinate generation with region token referencing, adding plug‑in modules such as a proposal generator, a hybrid fine‑grained encoder, and a region‑language connector to give any pretrained visual language model accurate, fine‑grained perception while preserving its original capabilities.

AI researchMultimodalPlug-and-Play
0 likes · 15 min read
How VLM‑FO1 Turns Vision‑Language Models into Precise Perception Machines
Data Party THU
Data Party THU
Oct 29, 2025 · Artificial Intelligence

Can Test-Time Scaling Unlock More Reliable Vision‑Language‑Action Robots?

The paper introduces RoboMonkey, a framework that applies a generate‑and‑verify paradigm and test‑time scaling to Vision‑Language‑Action models, showing that increasing sampling and verification at inference dramatically reduces action error across multiple VLA architectures, and presents scalable verifier training, synthetic data augmentation, and efficient deployment strategies.

AI researchAction VerificationRoboMonkey
0 likes · 8 min read
Can Test-Time Scaling Unlock More Reliable Vision‑Language‑Action Robots?
DataFunTalk
DataFunTalk
Oct 29, 2025 · Artificial Intelligence

OpenAI Unveils $25B AI Initiative and Multi‑Year AGI Roadmap

OpenAI’s recent restructuring created the OpenAI Foundation, pledged $25 billion to health and AI‑resilience research, outlined a multi‑year AGI timeline, announced plans for AI hardware, and set milestones for an AI research intern by next September and a fully autonomous AI researcher by 2028.

AGIAI hardwareAI research
0 likes · 3 min read
OpenAI Unveils $25B AI Initiative and Multi‑Year AGI Roadmap
Data Party THU
Data Party THU
Oct 20, 2025 · Artificial Intelligence

How Agentic RL Enables a 14B LLM to Outperform Giant Models – Inside rStar2‑Agent

This article analyzes the rStar2‑Agent paper, revealing how Agentic Reinforcement Learning, the GRPO‑RoC algorithm, a high‑throughput code‑execution service, and a three‑stage training recipe let a modest 14‑billion‑parameter model surpass much larger LLMs on challenging math benchmarks.

AI researchArtificial IntelligenceLLM
0 likes · 18 min read
How Agentic RL Enables a 14B LLM to Outperform Giant Models – Inside rStar2‑Agent
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Oct 18, 2025 · Artificial Intelligence

Time Series Paper Digest (Oct 11‑17 2025): FIRE, CauchyNet, EvoRate, CoRA

From Oct 11‑17 2025, this digest presents four recent AI papers on time‑series forecasting: FIRE introduces a frequency‑domain decomposition with independent amplitude‑phase modeling and adaptive weighting; CauchyNet leverages holomorphic activations for compact, data‑efficient learning; the EvoRate framework quantifies learnability via mutual information; and CoRA adds covariate‑aware adaptation to foundation models, all reporting significant accuracy gains and enhanced interpretability.

AI researchTime Series Forecastingcovariate-aware adaptation
0 likes · 10 min read
Time Series Paper Digest (Oct 11‑17 2025): FIRE, CauchyNet, EvoRate, CoRA
Meituan Technology Team
Meituan Technology Team
Oct 15, 2025 · Artificial Intelligence

What’s New in Large Model Research? Top Meituan AI Papers Up to Oct 2025

This curated list showcases Meituan’s latest large‑model breakthroughs and academic papers up to October 2025, spanning LLM system optimizations, multimodal generation, evaluation benchmarks, quantization techniques, and reinforcement‑learning‑driven improvements, offering researchers valuable insights and resources across the AI landscape.

AI researchBenchmarkingLarge Language Models
0 likes · 10 min read
What’s New in Large Model Research? Top Meituan AI Papers Up to Oct 2025
DataFunTalk
DataFunTalk
Oct 9, 2025 · Artificial Intelligence

From Physics to DeepMind: How a Tsinghua Star Is Shaping AI Research

Google DeepMind hired Shunyu Yao, a Tsinghua physics prodigy and former Anthropic researcher, whose rapid transition from theoretical physics to AI highlights the intense workload, values clash, and the accelerating pace of large‑model research.

AI researchCareer TransitionDeepMind
0 likes · 9 min read
From Physics to DeepMind: How a Tsinghua Star Is Shaping AI Research
Data Party THU
Data Party THU
Oct 1, 2025 · Artificial Intelligence

Why SFT and RL Are Two Sides of the Same Coin: A Unified Gradient Theory for LLM Post‑Training

This article analyzes a recent paper that unifies supervised fine‑tuning (SFT) and reinforcement learning (RL) for large language models under a single gradient estimator, introduces the Unified Policy Gradient Estimator (UPGE) and the Hybrid Post‑Training (HPT) algorithm, and demonstrates their superior performance on math reasoning benchmarks.

AI researchHybrid TrainingLLM
0 likes · 11 min read
Why SFT and RL Are Two Sides of the Same Coin: A Unified Gradient Theory for LLM Post‑Training
AIWalker
AIWalker
Sep 23, 2025 · Artificial Intelligence

Manzano: A Small 3B Multimodal Model That Unifies Image Understanding and Generation with SOTA Performance

Manzano introduces a hybrid vision tokenizer and a three‑stage training recipe that let a 3‑billion‑parameter multimodal LLM achieve state‑of‑the‑art results on both image‑understanding benchmarks and text‑to‑image generation, while scaling smoothly to larger sizes and minimizing task conflict.

AI researchManzanoMultimodal
0 likes · 25 min read
Manzano: A Small 3B Multimodal Model That Unifies Image Understanding and Generation with SOTA Performance
Amap Tech
Amap Tech
Sep 19, 2025 · Artificial Intelligence

How FSDrive Uses Spatio‑Temporal CoT to Revolutionize Autonomous Driving

FSDrive introduces a spatio‑temporal chain‑of‑thought approach that enables visual language models to generate future driving scenes as images, improving trajectory planning accuracy and safety by eliminating cross‑modal gaps and enforcing physical constraints in autonomous driving.

AI researchautonomous drivingspatio-temporal CoT
0 likes · 10 min read
How FSDrive Uses Spatio‑Temporal CoT to Revolutionize Autonomous Driving
Data Party THU
Data Party THU
Sep 18, 2025 · Artificial Intelligence

How Reinforcement Learning is Shaping the Future of Large Reasoning Models

This article surveys recent advances in applying reinforcement learning to large reasoning models, outlining the historical background, key breakthroughs like OpenAI o1 and DeepSeek‑R1, current challenges in reward design and scalability, and future research directions toward more capable AI systems.

AI researchRLHFreasoning
0 likes · 9 min read
How Reinforcement Learning is Shaping the Future of Large Reasoning Models
DataFunTalk
DataFunTalk
Sep 18, 2025 · Artificial Intelligence

How Tongyi DeepResearch Turns Chatty AI into a Research Powerhouse

Tongyi DeepResearch, an open‑source AI model and framework, achieves SOTA on multiple Deep Research benchmarks by combining fully open‑source models, frameworks, and data pipelines, and introduces novel agentic pre‑training, fine‑tuning, and reinforcement‑learning methods to enable complex multi‑step reasoning and real‑world applications.

AI researchagentic reinforcement learningopen-source
0 likes · 14 min read
How Tongyi DeepResearch Turns Chatty AI into a Research Powerhouse
AntTech
AntTech
Sep 13, 2025 · Artificial Intelligence

LLaDA‑MoE: The First Native MoE Diffusion Language Model Shattering Autoregressive Limits

Ant Group and Renmin University unveiled LLaDA‑MoE, the industry’s first native MoE‑based diffusion language model trained on 20 TB of data, achieving performance comparable to Qwen2.5 while delivering several‑fold faster inference, and the model will be fully open‑sourced to accelerate global AI research.

AI researchLLaDA-MoEMoE
0 likes · 6 min read
LLaDA‑MoE: The First Native MoE Diffusion Language Model Shattering Autoregressive Limits
DataFunTalk
DataFunTalk
Sep 12, 2025 · Artificial Intelligence

How Shunyu Yao is Shaping the Second Half of AI with Agents

Shunyu Yao, a Princeton‑trained AI researcher who rose through Tsinghua’s elite Yao class and OpenAI, is known for pioneering works like Tree of Thoughts, SWE‑bench, and ReAct, and now focuses on building general‑purpose agents and exploring the “second half” of AI development.

AI researchAgentReAct
0 likes · 12 min read
How Shunyu Yao is Shaping the Second Half of AI with Agents
Data Party THU
Data Party THU
Sep 9, 2025 · Artificial Intelligence

From Chain‑of‑Thought to Graph‑of‑Thought: The Evolution of LLM Reasoning

This article examines how large language model reasoning has progressed from linear Chain‑of‑Thought prompting to parallel Tree‑of‑Thought and flexible Graph‑of‑Thought approaches, highlighting each method’s mechanism, strengths, limitations, computational costs, and the broader shift toward cognitive‑centric AI research.

AI researchGraph-of-ThoughtTree of Thought
0 likes · 7 min read
From Chain‑of‑Thought to Graph‑of‑Thought: The Evolution of LLM Reasoning
Tencent Technical Engineering
Tencent Technical Engineering
Sep 6, 2025 · Artificial Intelligence

ARC Lab’s Blueprint: Turning Multimodal AI Research into Real-World Impact

The article outlines ARC Lab’s evolution from its 2019 founding as an internal corporate research unit to a high‑impact AI team that pursues difficult multimodal understanding and generation problems, measures success through a technology‑impact funnel, publishes 30‑40 top‑tier papers annually, and translates research into open‑source tools and products that drive academic, industry, business, and societal value.

AI researchMultimodal ModelsTechnology Impact
0 likes · 19 min read
ARC Lab’s Blueprint: Turning Multimodal AI Research into Real-World Impact
Data Party THU
Data Party THU
Sep 1, 2025 · Artificial Intelligence

Why Intermediate Tokens Make LLMs Reason Better: Insights from Denny Zhou

The article analyzes Denny Zhou's Stanford CS25 lecture on large language model reasoning, explaining how intermediate token generation, chain‑of‑thought prompting, self‑consistency, reinforcement‑learning fine‑tuning, and answer aggregation together unlock powerful reasoning capabilities beyond traditional greedy decoding.

AI researchLLMPrompt Engineering
0 likes · 17 min read
Why Intermediate Tokens Make LLMs Reason Better: Insights from Denny Zhou
Volcano Engine Developer Services
Volcano Engine Developer Services
Aug 26, 2025 · Artificial Intelligence

From Single LLM to Multi‑Agent: How Context Engineering Drives the Next AI Architecture

This article examines the evolution of LangChain's Open Deep Research project from a monolithic LLM pipeline to a multi‑agent system, highlighting the role of context engineering, architectural trade‑offs, practical code examples, and best‑practice guidelines for building scalable, token‑efficient AI solutions.

AI researchContext EngineeringLLM architecture
0 likes · 16 min read
From Single LLM to Multi‑Agent: How Context Engineering Drives the Next AI Architecture
Baidu Geek Talk
Baidu Geek Talk
Aug 25, 2025 · Artificial Intelligence

How ERNIE‑4.5‑VL Redefines Multimodal AI with 100+ Language Support

The ERNIE‑4.5‑VL visual‑language model breaks single‑modality limits by delivering breakthrough image, video, and text understanding across more than 100 languages, offering lightweight yet competitive performance against models like Qwen2.5‑VL, supporting 128K context, dual “thinking” modes, and extensive deployment resources.

AI researchERNIElarge language model
0 likes · 4 min read
How ERNIE‑4.5‑VL Redefines Multimodal AI with 100+ Language Support
Kuaishou Tech
Kuaishou Tech
Aug 23, 2025 · Artificial Intelligence

How Thyme Enables Models to Think Beyond Images with Code‑Driven Multimodal Reasoning

The Kwai Keye team presents Thyme, a novel multimodal reasoning framework that lets large language models generate and safely execute Python code for image manipulation and complex calculations, achieving significant performance gains over existing vision‑language models across perception, reasoning, and hallucination‑reduction benchmarks.

AI researchMultimodalcode generation
0 likes · 12 min read
How Thyme Enables Models to Think Beyond Images with Code‑Driven Multimodal Reasoning
AI Frontier Lectures
AI Frontier Lectures
Jul 31, 2025 · Artificial Intelligence

What’s Driving the Latest LLM Architecture Trends? DeepSeek, OLMo, Gemma, and More Explained

This article examines the evolution of large language model architectures over the past seven years, comparing key design choices such as Multi‑Head Latent Attention, Grouped‑Query Attention, Mixture‑of‑Experts, sliding‑window attention, normalization placement, and optimizer variants across models like DeepSeek V3, OLMo 2, Gemma 3, Llama 4, Qwen 3, SmolLM 3, and Kimi 2.

AI researchAttention MechanismsLLM comparison
0 likes · 30 min read
What’s Driving the Latest LLM Architecture Trends? DeepSeek, OLMo, Gemma, and More Explained
AI Frontier Lectures
AI Frontier Lectures
Jul 31, 2025 · Artificial Intelligence

Can a 32‑Token Compressor Generate Images Without Training?

This article reviews a recent study that demonstrates how a highly compressed one‑dimensional tokenizer, using only 32 discrete tokens and gradient‑based test‑time optimization, can generate high‑quality images without training a separate generative model, and explores its methodology, findings, applications, and limitations.

1D tokenizerAI researchTiTok
0 likes · 10 min read
Can a 32‑Token Compressor Generate Images Without Training?
Data Thinking Notes
Data Thinking Notes
Jul 30, 2025 · Artificial Intelligence

Tracing the Evolution of Large Language Models: Key Papers and Breakthroughs

This article reviews the most influential papers in large language model research since 2017, covering foundational works such as the Transformer, GPT‑3, BERT, scaling laws, and recent innovations like FlashAttention, Mamba, and QLoRA, highlighting their core contributions and impact on AI development.

AI researchLarge Language ModelsModel Optimization
0 likes · 28 min read
Tracing the Evolution of Large Language Models: Key Papers and Breakthroughs
Kuaishou Tech
Kuaishou Tech
Jul 22, 2025 · Artificial Intelligence

How Orthus Achieves Lossless Multimodal Generation with a Unified Autoregressive Transformer

Orthus, a new unified multimodal model presented at ICML 2025, leverages an autoregressive Transformer backbone with separate language and diffusion heads to enable lossless image‑text interleaved generation, outperforming existing models on both understanding and generation benchmarks while remaining computationally efficient.

AI researchautoregressive transformerdiffusion models
0 likes · 11 min read
How Orthus Achieves Lossless Multimodal Generation with a Unified Autoregressive Transformer
DataFunTalk
DataFunTalk
Jul 20, 2025 · Artificial Intelligence

Why Meta’s AI Pioneer Yang Li‑kun Is Being Marginalized: Power Struggles Behind the Scenes

The article examines how Meta’s CEO Mark Zuckerberg’s aggressive talent‑buying and commercial focus have sidelined Turing‑award winner Yang Li‑kun, detailing the restructuring of Meta’s AI labs, the clash over research directions, and the broader dilemma of balancing academic innovation with business imperatives in the AI industry.

AI industryAI researchArtificial Intelligence
0 likes · 14 min read
Why Meta’s AI Pioneer Yang Li‑kun Is Being Marginalized: Power Struggles Behind the Scenes
DataFunTalk
DataFunTalk
Jul 16, 2025 · Artificial Intelligence

Inside OpenAI: Unfiltered Lessons on AI, Culture, and Rapid Product Launches

A former OpenAI engineer shares a candid, unfiltered account of the company's fast‑paced growth, bottom‑up research culture, engineering practices, product decisions, and the intense seven‑week sprint that delivered Codex, offering valuable insights for AI researchers, product managers, and tech leaders.

AI researchOpenAISoftware Engineering
0 likes · 22 min read
Inside OpenAI: Unfiltered Lessons on AI, Culture, and Rapid Product Launches
Baobao Algorithm Notes
Baobao Algorithm Notes
Jul 16, 2025 · Artificial Intelligence

What Small Labs Reveal About RL Training: Multi‑Stage, Entropy, and Resource Strategies

The article analyzes Skywork OR1's technical report, detailing how small‑scale teams use GRPO‑based reinforcement learning with multi‑stage training, advantage‑mask variants, high‑temperature sampling, adaptive entropy loss, and resource‑allocation tricks to improve large language model performance while avoiding premature entropy collapse.

AI researchentropy controlmulti-stage training
0 likes · 21 min read
What Small Labs Reveal About RL Training: Multi‑Stage, Entropy, and Resource Strategies
AI Frontier Lectures
AI Frontier Lectures
Jul 11, 2025 · Artificial Intelligence

How Llama Evolved: From Llama‑1 to Llama‑3 – Architecture, Data, and Performance Insights

This article provides a comprehensive technical analysis of Meta's Llama series, tracing the evolution from Llama‑1 through Llama‑2 to Llama‑3, detailing model architectures, training data pipelines, optimization methods, benchmark results, and the broader impact on the open‑source AI community.

AI researchLarge Language ModelsLlama
0 likes · 25 min read
How Llama Evolved: From Llama‑1 to Llama‑3 – Architecture, Data, and Performance Insights
Amap Tech
Amap Tech
Jul 9, 2025 · Artificial Intelligence

Bridging Human Perception and Video Motion Generation: VMBench & LD‑RPS

This article introduces VMBench, a perception‑aligned video motion generation benchmark with a five‑dimensional metric suite and meta‑guided prompt generation, and LD‑RPS, a zero‑shot unified image restoration framework using latent diffusion and recurrent posterior sampling, detailing their motivations, innovations, experiments, and future directions.

AI researchVideo Generationdiffusion models
0 likes · 14 min read
Bridging Human Perception and Video Motion Generation: VMBench & LD‑RPS
iQIYI Technical Product Team
iQIYI Technical Product Team
Jul 3, 2025 · Artificial Intelligence

Three iQIYI AI Papers Break New Ground at ACL 2025 & INTERSPEECH 2025

iQIYI’s AI research team secured three paper acceptances—two at ACL 2025 (including a main conference and a Findings paper) and one at INTERSPEECH 2025—covering long‑context large language model evaluation, Chinese novel summarization, and efficient Thai speech recognition, with links to each work.

ACL 2025AI researchINTERSPEECH 2025
0 likes · 7 min read
Three iQIYI AI Papers Break New Ground at ACL 2025 & INTERSPEECH 2025
Kuaishou Tech
Kuaishou Tech
Jul 2, 2025 · Artificial Intelligence

How EvoSearch Supercharges Image and Video Generation with Test‑Time Evolutionary Search

EvoSearch, a test‑time evolutionary search method, dramatically improves image and video generation by increasing inference compute without extra training, outperforming existing scaling techniques on diffusion and flow models while maintaining robustness and diversity across multiple benchmarks.

AI researchEvolutionary SearchVideo Generation
0 likes · 8 min read
How EvoSearch Supercharges Image and Video Generation with Test‑Time Evolutionary Search
DataFunSummit
DataFunSummit
Jun 30, 2025 · Artificial Intelligence

How Large Language Models Are Evolving Toward Autonomous Meta‑Learning Agents

This talk reviews the rapid evolution of generative large‑model AI from rule‑based systems to massive pre‑training, examines the current bottlenecks in continual learning and knowledge discovery, and proposes large‑scale meta‑learning—especially context‑based reinforcement learning (ICRL)—as a path toward truly autonomous, self‑learning agents.

AI researchAutonomous AgentsLarge Language Models
0 likes · 24 min read
How Large Language Models Are Evolving Toward Autonomous Meta‑Learning Agents
DataFunTalk
DataFunTalk
Jun 27, 2025 · Artificial Intelligence

How Generative AI is Revolutionizing Ad Recommendation Systems

Join Baidu senior algorithm engineer Ji Zhi at the DataFun Summit 2025 to explore how generative AI transforms ad recommendation recall, covering item representation, evolving solution architectures, long‑sequence challenges, and practical insights for building efficient large‑model recommendation systems.

AI researchAd TechBaidu
0 likes · 3 min read
How Generative AI is Revolutionizing Ad Recommendation Systems
AIWalker
AIWalker
Jun 24, 2025 · Artificial Intelligence

How Multimodal Fusion Accelerates Paper Publication: Key Insights and Resources

The article surveys 117 recent multimodal‑fusion papers, classifies them into improvement‑based and combination‑based approaches, highlights representative works such as TimeXL, OGP‑Net, MMR‑Mamba and FusionSight, and provides a free collection of papers, classic models and code repositories for researchers.

AI researchMultimodal Fusioncomputer vision
0 likes · 8 min read
How Multimodal Fusion Accelerates Paper Publication: Key Insights and Resources
AI Frontier Lectures
AI Frontier Lectures
Jun 20, 2025 · Artificial Intelligence

How GCA Achieves 1000× Length Generalization in Large Language Models

Ant Research introduces GCA, a causal retrieval‑based grouped cross‑attention mechanism that end‑to‑end learns to fetch relevant past chunks, dramatically reducing memory usage and achieving over 1000× length generalization on long‑context language modeling tasks, with near‑constant inference memory and linear training cost.

AI researchGrouped Cross AttentionLLM efficiency
0 likes · 11 min read
How GCA Achieves 1000× Length Generalization in Large Language Models
Kuaishou Audio & Video Technology
Kuaishou Audio & Video Technology
Jun 11, 2025 · Artificial Intelligence

Kuaishou Showcases 12 Cutting-Edge CVPR 2025 Papers on Video Generation and AI

Kuaishou presented twelve peer‑reviewed papers at CVPR 2025 covering video quality assessment, large‑scale video datasets, dynamic 3D avatar reconstruction, 4D scene simulation, controllable video generation, scaling laws for diffusion transformers, multimodal foundations, and more, highlighting the company's leading research in computer vision and AI.

AI researchCVPR2025Multimodal
0 likes · 21 min read
Kuaishou Showcases 12 Cutting-Edge CVPR 2025 Papers on Video Generation and AI
AI Frontier Lectures
AI Frontier Lectures
Jun 9, 2025 · Artificial Intelligence

How DiSA Accelerates Autoregressive Image Generation with Diffusion Step Annealing

The article introduces DiSA, a training‑free diffusion step annealing technique that dramatically speeds up autoregressive image generation by reducing diffusion steps in later generation phases while preserving high visual quality, and validates the method across several state‑of‑the‑art AR‑Diffusion models.

AI researchDiSAautoregressive
0 likes · 16 min read
How DiSA Accelerates Autoregressive Image Generation with Diffusion Step Annealing
AI Algorithm Path
AI Algorithm Path
Jun 8, 2025 · Artificial Intelligence

Autoregressive vs Diffusion Language Models: Principles, Trade‑offs, and Future Directions

The article compares autoregressive and diffusion language models, detailing their mathematical foundations, training and inference pipelines, performance trade‑offs such as speed, coherence and diversity, and explores hybrid approaches and emerging research directions for more efficient and controllable text generation.

AI researchHybrid ModelsTransformer
0 likes · 17 min read
Autoregressive vs Diffusion Language Models: Principles, Trade‑offs, and Future Directions
DataFunTalk
DataFunTalk
Jun 8, 2025 · Artificial Intelligence

Why Autoregressive Video Models Like MAGI-1 May Outperform Diffusion Approaches

The article examines the current dominance of diffusion models in commercial video generation, contrasts them with autoregressive methods, and details how the open‑source MAGI‑1 model combines both paradigms to achieve longer, more controllable video synthesis while addressing scalability and quality challenges.

AI researchAutoregressive ModelsMAGI-1
0 likes · 70 min read
Why Autoregressive Video Models Like MAGI-1 May Outperform Diffusion Approaches
Architect
Architect
Jun 7, 2025 · Artificial Intelligence

Mass Framework: Boosting Multi‑Agent Design with Smarter Prompts & Topologies

The Mass framework, developed by Google and Cambridge University, automates multi‑agent system design by jointly optimizing prompts and topologies through three staged processes, demonstrating significant performance gains over existing methods across various tasks while highlighting the importance of coordinated prompt‑topology optimization.

AI researchMass frameworkTopology Design
0 likes · 6 min read
Mass Framework: Boosting Multi‑Agent Design with Smarter Prompts & Topologies
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Jun 6, 2025 · Artificial Intelligence

How dots.llm1 Sets New Benchmarks for Open‑Source MoE Language Models

dots.llm1, an open‑source 142‑billion‑parameter Mixture‑of‑Experts language model from hi lab, achieves Qwen2.5‑72B‑level performance after training on 11.2 T high‑quality tokens, and the release includes full models, intermediate checkpoints, and detailed training pipelines for the research community.

AI researchMixture of Expertslarge language model
0 likes · 10 min read
How dots.llm1 Sets New Benchmarks for Open‑Source MoE Language Models
Alibaba Cloud Developer
Alibaba Cloud Developer
Jun 5, 2025 · Artificial Intelligence

How Deep (Re)Search Transforms Code Search and AI-Powered Knowledge Retrieval

This article systematically explains the concepts of Deep Search and Deep Research, contrasts them with traditional Retrieval‑Augmented Generation, reviews leading commercial and open‑source solutions, details their architecture for code retrieval, and outlines future plans for specialized code‑search agents.

AI researchCode searchDeep Search
0 likes · 13 min read
How Deep (Re)Search Transforms Code Search and AI-Powered Knowledge Retrieval
Kuaishou Tech
Kuaishou Tech
Jun 4, 2025 · Artificial Intelligence

KwaiCoder-AutoThink-preview: An Automatic‑Thinking Large Model Enhanced with Step‑SRPO Reinforcement Learning

The KwaiPilot team released the KwaiCoder‑AutoThink‑preview model, which introduces a novel automatic‑thinking training paradigm and a process‑supervised reinforcement‑learning method called Step‑SRPO, enabling the model to dynamically switch between thinking and non‑thinking modes, reduce inference cost, and achieve up to 20‑point gains on code and math benchmarks while handling large‑scale codebases.

AI researchModel Optimizationautomatic thinking
0 likes · 12 min read
KwaiCoder-AutoThink-preview: An Automatic‑Thinking Large Model Enhanced with Step‑SRPO Reinforcement Learning
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Jun 3, 2025 · Artificial Intelligence

Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation

The TailoredBench framework dramatically reduces large‑language‑model evaluation cost and error by using a global probe set, model‑specific source selection, extensible K‑Medoids clustering, and calibration, achieving up to 300× speedup and a 31.4% MAE reduction across diverse benchmarks.

AI researchK-MedoidsLLM evaluation
0 likes · 10 min read
Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation
AntTech
AntTech
May 31, 2025 · Artificial Intelligence

Machine Reasoning and Deep Thinking: Insights from Ant Financial’s NLP Lead Wu Wei

The article explores how DeepSeek R1 and long‑thinking chains have revived interest in machine reasoning, tracing the evolution of natural‑language models, defining reasoning as logical knowledge composition, and outlining future research directions in efficient reasoning architectures and deep‑thinking applications.

AI researchEfficient ReasoningLarge Language Models
0 likes · 8 min read
Machine Reasoning and Deep Thinking: Insights from Ant Financial’s NLP Lead Wu Wei
ShiZhen AI
ShiZhen AI
May 28, 2025 · Artificial Intelligence

Claude Finally Gets Voice: Anthropic Adds Speech to Its AI Assistant

Anthropic has introduced a voice mode for Claude, enabling English users to speak and type interchangeably with five voice personalities, while a new 3D AI startup, SpAItial, showcases photorealistic room generation and researchers present INTUITOR, a confidence‑driven training method that improves AI reasoning.

AI researchAnthropicClaude
0 likes · 7 min read
Claude Finally Gets Voice: Anthropic Adds Speech to Its AI Assistant
AI Frontier Lectures
AI Frontier Lectures
May 28, 2025 · Artificial Intelligence

How Token‑Shuffle Enables 2048×2048 Autoregressive Image Generation

The article analyzes the Token‑Shuffle method, which reduces visual token redundancy to allow high‑resolution (2048×2048) autoregressive image generation, detailing its architecture, training pipeline, experimental results, efficiency gains, and comparisons with diffusion and other AR models.

AI researchAutoregressive Modelshigh-resolution image generation
0 likes · 17 min read
How Token‑Shuffle Enables 2048×2048 Autoregressive Image Generation
AI Frontier Lectures
AI Frontier Lectures
May 27, 2025 · Artificial Intelligence

Can One-Step Generative Modeling Beat Multi-Step Diffusion? Inside MeanFlow

The article presents MeanFlow, a novel one‑step generative modeling framework that replaces instantaneous velocity with an average‑velocity field, achieving a record‑low FID of 3.43 on ImageNet 256×256 with a single function evaluation and outperforming both prior single‑step and multi‑step diffusion models.

AI researchFIDFlow Matching
0 likes · 7 min read
Can One-Step Generative Modeling Beat Multi-Step Diffusion? Inside MeanFlow
Baobao Algorithm Notes
Baobao Algorithm Notes
May 26, 2025 · Artificial Intelligence

When Should Large Language Models Think? 10 Cutting‑Edge Strategies to Boost Reasoning Efficiency

This article reviews ten recent papers that tackle the over‑thinking problem in large language models by shortening chain‑of‑thought reasoning, introducing dynamic early‑exit, adaptive thinking triggers, and reinforcement‑learning‑based training, showing how models can maintain or improve accuracy while dramatically reducing token usage and latency.

AI researchModel Pruningadaptive inference
0 likes · 38 min read
When Should Large Language Models Think? 10 Cutting‑Edge Strategies to Boost Reasoning Efficiency
JD Tech
JD Tech
May 20, 2025 · Artificial Intelligence

How Re‑parameterization and Adaptive Learning Boost Visual Deep Learning Efficiency

The award‑winning project from Tsinghua University and JD Retail introduces re‑parameterization model design, cross‑scene adaptive learning, and platform‑aware compression to overcome accuracy‑efficiency trade‑offs in visual deep learning, achieving over 20% accuracy gains and more than 50% inference speedup in real‑world e‑commerce deployments.

AI researchadaptive modelscomputer vision
0 likes · 6 min read
How Re‑parameterization and Adaptive Learning Boost Visual Deep Learning Efficiency
AI Frontier Lectures
AI Frontier Lectures
May 19, 2025 · Artificial Intelligence

DreamO: Multi‑Condition Image Customization with a 400M Flux‑Based Model

DreamO, a collaborative effort by ByteDance and Peking University, introduces a unified 400M‑parameter framework built on Flux‑1.0‑dev that enables simultaneous control of identity, style, appearance, and virtual try‑on, offering open‑source, low‑cost, and fast image customization comparable to commercial large models.

AI researchDreamOFlux model
0 likes · 6 min read
DreamO: Multi‑Condition Image Customization with a 400M Flux‑Based Model
Amap Tech
Amap Tech
May 19, 2025 · Artificial Intelligence

Group Policy Gradient: Direct Objective Optimization for Faster Reinforcement Learning

The article introduces Group Policy Gradient (GPG), a reinforcement‑learning framework that eliminates surrogate loss functions and critic models, directly optimizes the original objective, reduces bias and variance, and achieves state‑of‑the‑art performance on both single‑modal and multimodal tasks.

AI researchLLM fine-tuningbias reduction
0 likes · 7 min read
Group Policy Gradient: Direct Objective Optimization for Faster Reinforcement Learning
Amap Tech
Amap Tech
May 12, 2025 · Artificial Intelligence

How G3PT Uses Autoregressive Modeling to Revolutionize 3D Generation

The paper introduces G3PT, a groundbreaking autoregressive 3D generation model that employs a Cross‑Scale Querying Transformer and multi‑scale tokenization to produce high‑quality meshes from a single image, outperforming diffusion‑based methods and revealing a scaling law for 3D generation.

3D GenerationAI researchG3PT
0 likes · 9 min read
How G3PT Uses Autoregressive Modeling to Revolutionize 3D Generation
AI Frontier Lectures
AI Frontier Lectures
May 10, 2025 · Artificial Intelligence

Can the ‘Canon’ Layer Unlock New Limits in Large Language Models?

A new study introduces the lightweight “Canon” layer for large language models, showing how it improves information flow, inference depth, and scalability across Transformers, linear attention, and state‑space architectures, while offering a controlled synthetic pre‑training benchmark for deeper architectural analysis.

AI researchLarge Language ModelsMamba
0 likes · 11 min read
Can the ‘Canon’ Layer Unlock New Limits in Large Language Models?
Baobao Algorithm Notes
Baobao Algorithm Notes
Apr 28, 2025 · Artificial Intelligence

What Makes Qwen3 the Next Leap in Large Language Models?

The article announces Qwen3, detailing its flagship 235B and smaller MoE models, superior benchmark performance, extensive multilingual support, expanded pretraining data, four-stage post‑training, flexible thinking modes, deployment guides for SGLang, vLLM, Ollama, and future plans toward AGI‑level capabilities.

AI researchQwen3deployment
0 likes · 15 min read
What Makes Qwen3 the Next Leap in Large Language Models?
DataFunTalk
DataFunTalk
Apr 25, 2025 · Artificial Intelligence

Does Reinforcement Learning Really Expand Reasoning Capacity in Large Language Models? Insights from Recent Empirical Study

Recent empirical research by Tsinghua’s LeapLab and Shanghai Jiao Tong University reveals that reinforcement‑learning‑based fine‑tuning (RLVR) improves sampling efficiency but does not extend the fundamental reasoning abilities of large language models beyond their base capabilities, as demonstrated across mathematics, code, and visual reasoning benchmarks.

AI researchLarge Language ModelsRLVR
0 likes · 12 min read
Does Reinforcement Learning Really Expand Reasoning Capacity in Large Language Models? Insights from Recent Empirical Study
Architect
Architect
Apr 21, 2025 · Artificial Intelligence

Microsoft Research Releases BitNet b1.58 2B4T: A 1‑Bit Native Large Language Model with Ultra‑Low Memory and Energy Consumption

Microsoft Research introduced BitNet b1.58 2B4T, a native 1‑bit large language model with 2 billion parameters trained on 4 trillion tokens, achieving only 0.4 GB non‑embedding memory, 0.028 J decoding energy, and 29 ms CPU latency while matching full‑precision performance.

1-bit LLMAI researchBitNet
0 likes · 7 min read
Microsoft Research Releases BitNet b1.58 2B4T: A 1‑Bit Native Large Language Model with Ultra‑Low Memory and Energy Consumption
21CTO
21CTO
Apr 17, 2025 · Artificial Intelligence

What’s New in OpenAI’s GPT‑4.1? Bigger Context, Faster, Cheaper AI

OpenAI has launched GPT‑4.1, a multimodal AI model that expands context windows to one million tokens, improves coding and instruction following, offers cheaper Mini and Nano variants, and signals a shift in its release roadmap, including plans to retire GPT‑4 and delay GPT‑5.

AI researchGPT-4.1OpenAI
0 likes · 5 min read
What’s New in OpenAI’s GPT‑4.1? Bigger Context, Faster, Cheaper AI
Baobao Algorithm Notes
Baobao Algorithm Notes
Apr 16, 2025 · Artificial Intelligence

Why Reinforcement Learning Finally Works: The Second Half of AI

The article argues that AI has entered its second half, where reinforcement learning finally generalizes thanks to large‑scale language pretraining and reasoning, shifting focus from building ever better models to redefining problems, evaluation methods, and real‑world utility.

AI researchIndustry Trends
0 likes · 16 min read
Why Reinforcement Learning Finally Works: The Second Half of AI
DevOps
DevOps
Apr 13, 2025 · Artificial Intelligence

The Amazing Magic of GPT‑4o and a Speculative Technical Roadmap

This article reviews the breakthrough image‑generation capabilities of GPT‑4o, showcases diverse examples, and offers a detailed speculation on its underlying autoregressive architecture, tokenization methods, VQ‑VAE/GAN advances, and training strategies that could explain its performance.

AI researchGPT-4oVQ-VAE
0 likes · 16 min read
The Amazing Magic of GPT‑4o and a Speculative Technical Roadmap
AntTech
AntTech
Apr 10, 2025 · Artificial Intelligence

Ant Group Presents Four AI Research Papers at ICLR 2025 Live Showcase

At the ICLR 2025 live session in Singapore, Ant Group showcased four cutting‑edge papers—CodePlan, Animate‑X, Group Position Embedding, and OmniKV—demonstrating advances in large‑language‑model reasoning, universal character animation, layout‑aware document understanding, and efficient long‑context inference.

AI researchLarge Language ModelsMultimodal
0 likes · 6 min read
Ant Group Presents Four AI Research Papers at ICLR 2025 Live Showcase
DevOps
DevOps
Apr 7, 2025 · Artificial Intelligence

Meta Llama 4 Scout, Maverick, and Behemoth: Architecture, NoPE Innovation, and Training Advances

The article introduces Meta's newly open‑sourced Llama 4 series—including Scout with a 1 billion‑token context window, Maverick with 400 billion parameters, and the upcoming Behemoth teacher model—detailing their expert‑mix architecture, the NoPE positional‑encoding removal, training pipelines, performance benchmarks, and infrastructure improvements for large‑scale AI research.

AI researchLlama 4NoPE
0 likes · 8 min read
Meta Llama 4 Scout, Maverick, and Behemoth: Architecture, NoPE Innovation, and Training Advances
AntTech
AntTech
Mar 31, 2025 · Artificial Intelligence

Ant Group Papers Accepted at ICLR 2025: Summaries and Links

The article presents the abstracts, publication types, links, and research areas of seventeen Ant Group papers accepted at ICLR 2025, covering topics such as embodied robot co‑design, efficient distributed training for large language models, optimization via LLMs, character animation, interactive frame interpolation, KV‑cache management, and privacy‑preserving Transformers.

AI researchAnt GroupICLR2025
0 likes · 23 min read
Ant Group Papers Accepted at ICLR 2025: Summaries and Links
AI Frontier Lectures
AI Frontier Lectures
Mar 30, 2025 · Artificial Intelligence

Do Large Language Models Mirror Human Brain Language Processing? Google’s Groundbreaking Findings

Google researchers discovered a linear relationship between brain activity recorded during natural conversation and the internal embeddings of a speech‑to‑text large language model, revealing that acoustic and lexical representations from the model can accurately predict neural responses in both language comprehension and production.

AI researchGoogleLarge Language Models
0 likes · 8 min read
Do Large Language Models Mirror Human Brain Language Processing? Google’s Groundbreaking Findings
AI Frontier Lectures
AI Frontier Lectures
Mar 30, 2025 · Artificial Intelligence

How NOVA Generates High‑Quality Video Autoregressively Without Vector Quantization

This article provides an in‑depth analysis of the NOVA model, a non‑quantized autoregressive video generation framework that combines frame‑by‑frame temporal prediction with set‑by‑set spatial prediction, uses diffusion loss for token estimation, and achieves state‑of‑the‑art results on multiple video and image benchmarks.

AI researchAutoregressive ModelNova
0 likes · 15 min read
How NOVA Generates High‑Quality Video Autoregressively Without Vector Quantization
MaGe Linux Operations
MaGe Linux Operations
Mar 26, 2025 · Artificial Intelligence

Why Qwen2.5‑VL‑32B Is the New AI Breakthrough for Vision and Math

Alibaba's newly released Qwen2.5‑VL‑32B multimodal model delivers state‑of‑the‑art visual and textual performance, offering human‑aligned responses, superior mathematical reasoning, fine‑grained image understanding, and efficient deployment features that make it a compelling tool for developers and AI researchers alike.

AI researchMultimodal ModelQwen2.5-VL-32B
0 likes · 9 min read
Why Qwen2.5‑VL‑32B Is the New AI Breakthrough for Vision and Math
AI Frontier Lectures
AI Frontier Lectures
Mar 25, 2025 · Artificial Intelligence

What Drives Alignment in Multimodal Large Language Models? A Comprehensive Review

This article provides an in‑depth review of alignment algorithms for multimodal large language models, covering application scenarios, dataset construction methods, evaluation benchmarks, current challenges, and future research directions, while summarizing contributions from leading academic institutions.

AI researchDataset ConstructionMultimodal LLM
0 likes · 22 min read
What Drives Alignment in Multimodal Large Language Models? A Comprehensive Review
AI Algorithm Path
AI Algorithm Path
Mar 20, 2025 · Artificial Intelligence

Understanding Multimodal Large Language Models: Recent Advances and Comparative Analysis

This article surveys the latest multimodal large language model research, dissecting the design, training strategies, and performance trade‑offs of models such as Llama 3.2, Molmo, NVLM, Qwen2‑VL, Pixtral, MM1.5, Emu3, and Janus, and highlights the challenges of fair cross‑model evaluation.

AI researchLarge Language ModelsModel Training Strategies
0 likes · 16 min read
Understanding Multimodal Large Language Models: Recent Advances and Comparative Analysis
AIWalker
AIWalker
Mar 14, 2025 · Artificial Intelligence

Dynamic Tanh Lets He Kaiming and LeCun Drop Transformer Normalization in 9 Lines

Researchers He Kaiming, Yann LeCun and colleagues propose a 9‑line Dynamic Tanh (DyT) layer that replaces LayerNorm/RMSNorm in Transformers, showing comparable or superior accuracy across vision, language, speech and DNA tasks while also reducing inference latency on modern GPUs.

AI researchDynamic TanhTransformer
0 likes · 18 min read
Dynamic Tanh Lets He Kaiming and LeCun Drop Transformer Normalization in 9 Lines
AIWalker
AIWalker
Mar 11, 2025 · Artificial Intelligence

Introducing FAR: A Frequency‑Progressive Autoregressive Paradigm for Image Generation

The paper presents FAR, a frequency‑aware autoregressive framework that predicts image tokens from low‑frequency to high‑frequency components using a continuous tokenizer, and demonstrates its efficiency and quality on ImageNet and text‑to‑image benchmarks compared with existing AR and VAR methods.

AI researchAutoregressive ModelsFAR
0 likes · 20 min read
Introducing FAR: A Frequency‑Progressive Autoregressive Paradigm for Image Generation
AIWalker
AIWalker
Mar 5, 2025 · Artificial Intelligence

Attention Distillation in Diffusion Models: CVPR 2025 Technique Outperforms Traditional Image Generation

The paper introduces a novel attention‑distillation loss and a guided‑sampling scheme that together enable diffusion models to faithfully transfer visual features from reference images, dramatically speeding synthesis and surpassing prior plug‑and‑play attention methods across style transfer, text‑to‑image generation, and texture synthesis tasks.

AI researchStyle Transferattention distillation
0 likes · 15 min read
Attention Distillation in Diffusion Models: CVPR 2025 Technique Outperforms Traditional Image Generation
Data Thinking Notes
Data Thinking Notes
Mar 4, 2025 · Artificial Intelligence

Unlock AI-Powered Research: The DeepSeek‑R1 & DeepResearch Guide

Compiled by Tsinghua University experts, this guide systematically analyzes the DeepSeek‑R1 inference model and DeepResearch platform, offering multi‑model comparisons, real‑world case studies, and end‑to‑end AI‑driven solutions from data collection to report generation for researchers.

AI researchData AutomationDeepSeek
0 likes · 6 min read
Unlock AI-Powered Research: The DeepSeek‑R1 & DeepResearch Guide
Architect
Architect
Mar 3, 2025 · Artificial Intelligence

Unlocking Reasoning LLMs: Methods, DeepSeek R1 Insights, and Cost‑Effective Strategies

This article examines how to build and improve reasoning‑capable large language models, explains the definition and use‑cases of reasoning models, details DeepSeek‑R1’s training pipeline, compares four key enhancement methods—including inference‑time scaling, pure RL, SFT + RL, and distillation—and offers budget‑friendly advice.

AI researchDeepSeekInference Scaling
0 likes · 27 min read
Unlocking Reasoning LLMs: Methods, DeepSeek R1 Insights, and Cost‑Effective Strategies
Tencent Cloud Developer
Tencent Cloud Developer
Feb 27, 2025 · Artificial Intelligence

DeepSeek LLM Series (V1‑V3, R1) Technical Overview and Analysis

The DeepSeek technical overview details the evolution from the dense 67 B V1 model through the 236 B MoE‑based V2 and 671 B V3 with FP8 training, to the RL‑only R1 series that learns reasoning without supervision, highlighting innovations such as Grouped‑Query Attention, Multi‑Head Latent Attention, load‑balancing‑free MoE, Multi‑Token Prediction, and knowledge distillation, and reporting state‑of‑the‑art benchmark results and open‑source reproduction projects.

AI researchDeepSeekMixture of Experts
0 likes · 37 min read
DeepSeek LLM Series (V1‑V3, R1) Technical Overview and Analysis
Architecture Digest
Architecture Digest
Feb 25, 2025 · Artificial Intelligence

DeepSeek Distillation Technology: Overview, Innovations, Architecture, Training, Performance, and Challenges

DeepSeek’s distillation technology combines data and model distillation to transfer knowledge from large teacher models to compact student models, detailing its definitions, principles, key innovations, architecture, training methods, performance gains, and challenges, especially in multimodal contexts.

AI researchDeepSeekLarge Language Models
0 likes · 16 min read
DeepSeek Distillation Technology: Overview, Innovations, Architecture, Training, Performance, and Challenges
Architect
Architect
Feb 22, 2025 · Artificial Intelligence

How Open‑Source Projects Reproduced DeepSeek‑R1 and Pushed LLM Limits

This article reviews the most notable open‑source reproductions of DeepSeek‑R1—including Open R1, OpenThoughts, LIMO and DeepScaleR—detailing their data pipelines, training steps, reinforcement‑learning strategies, dataset constructions, and benchmark results that demonstrate how small, high‑quality data can rival massive‑scale models.

AI researchDataset ConstructionDeepSeek-R1
0 likes · 26 min read
How Open‑Source Projects Reproduced DeepSeek‑R1 and Pushed LLM Limits
NewBeeNLP
NewBeeNLP
Feb 21, 2025 · Artificial Intelligence

Do Scaling Laws Still Hold? Analyzing Grok‑3, Deepseek and LLM Training Trends

The article examines whether pre‑training scaling laws remain valid, compares Grok‑3’s architecture and training strategy with Deepseek models, and explores how different scaling approaches—pre‑training, RL‑based, and test‑time—affect the cost‑effectiveness and intelligence of large language models.

AI researchGrok 3scaling laws
0 likes · 11 min read
Do Scaling Laws Still Hold? Analyzing Grok‑3, Deepseek and LLM Training Trends
Architect
Architect
Feb 20, 2025 · Artificial Intelligence

Why Long CoT and In‑Context RL Are the Next Frontier for LLMs

The article analyses recent breakthroughs such as OpenAI's o1, Long CoT, and test‑time search, arguing that enabling LLMs to perform self‑critique and reinforcement learning with long output sequences is essential for future AI performance, while warning against overly structured workflows.

AI researchIn‑Context RLLLM
0 likes · 12 min read
Why Long CoT and In‑Context RL Are the Next Frontier for LLMs
AIWalker
AIWalker
Feb 20, 2025 · Artificial Intelligence

Transfusion: A Single Model for Unified Image Generation and Understanding

Transfusion is a 7B‑parameter transformer that jointly trains language modeling and diffusion losses on mixed text‑image data, enabling seamless text generation, image generation, and image understanding within one model and outperforming prior multimodal approaches such as Chameleon across multiple benchmarks.

AI researchMultimodalTransformer
0 likes · 20 min read
Transfusion: A Single Model for Unified Image Generation and Understanding
AIWalker
AIWalker
Feb 16, 2025 · Artificial Intelligence

VARGPT: A Unified Autoregressive Architecture for Multimodal Understanding and Generation

VARGPT is a novel multimodal large language model that unifies visual understanding and autoregressive image generation within a single architecture, extending LLaVA with next‑token and next‑scale prediction, trained through three staged data‑curated phases and achieving superior performance on numerous vision‑language benchmarks.

AI researchMultimodalVARGPT
0 likes · 20 min read
VARGPT: A Unified Autoregressive Architecture for Multimodal Understanding and Generation
Baobao Algorithm Notes
Baobao Algorithm Notes
Feb 13, 2025 · Artificial Intelligence

How to Build and Improve Reasoning LLMs: Methods, Trade‑offs, and DeepSeek Insights

This article explains what reasoning language models are, when they are needed, and reviews four main techniques— inference‑time scaling, pure reinforcement learning, combined SFT + RL, and distillation—illustrated with DeepSeek‑R1’s development, cost analysis, and low‑budget alternatives.

AI researchDeepSeekInference Scaling
0 likes · 27 min read
How to Build and Improve Reasoning LLMs: Methods, Trade‑offs, and DeepSeek Insights
ZhongAn Tech Team
ZhongAn Tech Team
Feb 10, 2025 · Artificial Intelligence

Weekly AI Technology Overview: OpenAI ChatGPT Search, Deep Research, DeepSeek Advances, and Industry Insights

This week’s AI roundup covers OpenAI’s fully open ChatGPT Search, the launch of Deep Research for automated multi‑step research, NetEase Youdao’s integration of DeepSeek‑R1, Figure’s robot partnership break with OpenAI, low‑cost AI model s1, OpenAI’s Stargate data‑center plans, Google’s antitrust probe, DeepSeek’s traffic surge, and top AI scientist Xu joining Alibaba.

AIAI researchChatGPT
0 likes · 9 min read
Weekly AI Technology Overview: OpenAI ChatGPT Search, Deep Research, DeepSeek Advances, and Industry Insights
Top Architect
Top Architect
Feb 9, 2025 · Artificial Intelligence

DeepSeek‑R1: Training Pipeline, Reinforcement‑Learning Techniques, and Experimental Results

The article reviews DeepSeek‑R1’s training methodology—including cold‑start data collection, multi‑stage RL fine‑tuning, SFT data generation, and model distillation—highlights its performance comparable to OpenAI‑o1‑1217, and discusses key contributions, reward design, successful experiments, and failed attempts.

AI researchDeepSeekLLM
0 likes · 12 min read
DeepSeek‑R1: Training Pipeline, Reinforcement‑Learning Techniques, and Experimental Results
Architect
Architect
Feb 6, 2025 · Artificial Intelligence

DeepSeek‑R1: Reinforcement‑Learning‑Driven Long‑Chain Reasoning for Large Language Models

The article reviews DeepSeek‑R1, detailing its reinforcement‑learning‑based training pipeline that uses minimal supervised data, cold‑start fine‑tuning, multi‑stage RL, rejection‑sampling SFT, and distillation to achieve reasoning performance comparable to OpenAI‑o1‑1217, while also discussing successful contributions and failed experiments.

AI researchDeepSeek-R1LLM reasoning
0 likes · 11 min read
DeepSeek‑R1: Reinforcement‑Learning‑Driven Long‑Chain Reasoning for Large Language Models