BestHub
Sign in
Machine Learning Algorithms & Natural Language Processing
Author

Machine Learning Algorithms & Natural Language Processing

Focused on frontier AI technologies, empowering AI researchers' progress.

586
Articles
0
Likes
2.9k
Views
0
Comments
Recent Articles

Latest from Machine Learning Algorithms & Natural Language Processing

100 recent articles max
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 11, 2026 · Artificial Intelligence

How Pi’s Harness Achieves a 99.93% Cache Hit Rate for DeepSeek and Cuts Cost Up to 7×

The open‑source Pi harness for DeepSeek delivers a 99.93% cache hit rate, reducing token‑processing costs to $0.028 per successful task—about seven times cheaper than Claude Code—while supporting extensible file‑operation tools and demonstrating dramatic cost differences across competing agent harnesses.

DeepSeekLLM CostPi
0 likes · 9 min read
How Pi’s Harness Achieves a 99.93% Cache Hit Rate for DeepSeek and Cuts Cost Up to 7×
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 11, 2026 · Artificial Intelligence

Bengio Team’s ERRLESS Boosts Symbolic Regression with 10× Faster Posterior Sampling

The paper introduces ERRLESS, a Bayesian symbolic regression framework that reformulates posterior sampling as a maximum‑entropy reinforcement‑learning problem, achieving ten‑fold speedups, robust noise handling, and state‑of‑the‑art performance on Feynman and Blackbox benchmarks.

AI researchGFlowNetbayesian inference
0 likes · 10 min read
Bengio Team’s ERRLESS Boosts Symbolic Regression with 10× Faster Posterior Sampling
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 11, 2026 · Artificial Intelligence

How DoGNAVY Ranked #3 Globally in AI Security Using a Single Open‑Source Model

DoGNAVY achieved a 90.84% verification rate and placed third on the CyberGym AI‑security leaderboard by leveraging the open‑source GLM‑5.2 model within a multi‑agent workflow that combines reachability analysis, dynamic testing, independent review, and a strict sandbox environment.

AI securityAgentDoGCyberGym benchmark
0 likes · 14 min read
How DoGNAVY Ranked #3 Globally in AI Security Using a Single Open‑Source Model
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 11, 2026 · Artificial Intelligence

Tsinghua’s TianMou Chip Team Returns to Nature Cover with Brain‑Inspired Complementary Vision Paradigm

The TianMou team at Tsinghua University expands its Nature‑cover breakthrough from a novel brain‑inspired complementary vision chip to a full self‑supervised algorithmic ecosystem that learns visual primitives without ground‑truth, delivers high‑dynamic‑range imaging, and powers downstream tasks such as depth estimation and video segmentation in extreme open‑world conditions.

Nature SensorsSelf-supervised LearningTianMouCV
0 likes · 15 min read
Tsinghua’s TianMou Chip Team Returns to Nature Cover with Brain‑Inspired Complementary Vision Paradigm
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 10, 2026 · Industry Insights

Why Cursor’s Brand Is Set to Vanish After SpaceX’s $60 B Acquisition

SpaceX is acquiring the AI‑coding startup Cursor for $60 billion, planning to retire the Cursor brand within months, integrate its data and technology into SpaceX AI, and reshape the competitive landscape of AI‑assisted programming amid mixed financial signals and developer concerns.

AI acquisitionAI marketCursor
0 likes · 7 min read
Why Cursor’s Brand Is Set to Vanish After SpaceX’s $60 B Acquisition
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 10, 2026 · Artificial Intelligence

Can Models Keep Getting Stronger After Deployment? SERPO Enables Label‑Free Self‑Evolution on Open‑Ended Tasks

The SERPO framework replaces answer‑voting with a self‑evolving rubric, allowing test‑time reinforcement learning to improve large language models on open‑ended tasks without any human labels, and demonstrates up to 73% of privileged‑supervision gains on benchmarks such as HealthBench and ResearchQA.

AI evaluationHealthBenchOpen-Ended Tasks
0 likes · 15 min read
Can Models Keep Getting Stronger After Deployment? SERPO Enables Label‑Free Self‑Evolution on Open‑Ended Tasks
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 10, 2026 · Artificial Intelligence

Training One‑Step Generative Models Without CFG, DMD, GAN, Drifting, or MeanFlow

The paper introduces TBSM, a lightweight direction‑tracking network that learns fake‑to‑real movement fields from three‑sample scattering events, enabling single‑forward‑pass generation and achieving state‑of‑the‑art FID scores on ImageNet and a 20B text‑to‑image model without relying on CFG, DMD, GAN, drifting, or mean‑flow techniques.

PixelDiTQwen-ImageTBSM
0 likes · 12 min read
Training One‑Step Generative Models Without CFG, DMD, GAN, Drifting, or MeanFlow
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 9, 2026 · Artificial Intelligence

Why Online RL (OPD, RLHF) Uses Reverse KL While Offline SFT Distillation Prefers Forward KL

The article explains that forward KL encourages a student model to cover all major teacher modes, whereas reverse KL seeks a single dominant mode, and shows why online reinforcement learning methods like OPD and RLHF adopt reverse KL while offline SFT distillation relies on forward KL.

KL DivergenceOPDRLHF
0 likes · 7 min read
Why Online RL (OPD, RLHF) Uses Reverse KL While Offline SFT Distillation Prefers Forward KL
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 9, 2026 · Artificial Intelligence

Why Large Models Excel at Table Lookup Yet Fail at Future Prediction – Insights from TopBench

TopBench, a new benchmark for implicit predictive reasoning in table question answering, shows that current large language models can retrieve tabular facts but often miss the hidden prediction intent, leading to low accuracy across four task types and revealing two key bottlenecks: intent alignment and robust modeling.

Implicit PredictionTable QATopBench
0 likes · 21 min read
Why Large Models Excel at Table Lookup Yet Fail at Future Prediction – Insights from TopBench