Skip to content
Tagged articles

Zero-Shot Learning

26 articles · Page 1 of 1
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 25, 2026 · Artificial Intelligence

RAX: Robot Agents Self-Improve via Online Exploration, Lead SOTA by 37.4%

Harvard, NVIDIA, Berkeley, MIT, and Stanford researchers introduce RAX, a framework where a coding agent autonomously explores robot perception and control interfaces, writes executable programs from successful trials, and accumulates reusable skills—achieving 37.4% average gains over prior state-of-the-art on five benchmarks without any human demonstrations or model fine-tuning.

Code as PolicyEmbodied AIMulti-Embodiment
0 likes · 15 min read
RAX: Robot Agents Self-Improve via Online Exploration, Lead SOTA by 37.4%
Machine Heart
Machine Heart
Oct 25, 2026 · Artificial Intelligence

RAX: Scaling Online Exploration Beats SOTA by 37.4% Across 5 Robot Benchmarks

Harvard, NVIDIA, Berkeley, MIT, and Stanford researchers introduce RAX, a framework that scales online exploration for robot agents, achieving 37.4% average improvement over state-of-the-art on five benchmarks without any human demonstrations, using frozen model parameters and self-generated code skills.

Code as PolicyEmbodied AIMulti-Embodiment
0 likes · 15 min read
RAX: Scaling Online Exploration Beats SOTA by 37.4% Across 5 Robot Benchmarks
Machine Heart
Machine Heart
Oct 24, 2026 · Artificial Intelligence

TabClustPFN: Out-of-the-Box Tabular Clustering with Probabilistic Cluster Count

Researchers from Renmin University, Rutgers, NUS, and MBZUAI introduce TabClustPFN, a prior-data fitted network that performs zero-shot clustering on tabular data via a single forward pass, automatically estimating the number of clusters and providing a probability distribution over candidate cluster counts, achieving competitive performance on 44 real-world datasets without per-dataset training.

Cluster Count EstimationNeurIPS 2026PFN
0 likes · 10 min read
TabClustPFN: Out-of-the-Box Tabular Clustering with Probabilistic Cluster Count
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 24, 2026 · Artificial Intelligence

HyperQ: 64 Qubits Enable 1.1B Model to Surpass 8B Models in Zero-Shot Tasks

Researchers from Université de Montréal and Mila introduce HyperQ, a quantum-augmented diffusion language model that uses a hypernetwork to generate token-adaptive quantum circuits; with 64 qubits, a 1.1B parameter model outperforms 8B models on six zero-shot benchmarks, and circuits are validated on IBM's 156-qubit quantum cluster.

HyperQHypernetworksIBM quantum cluster
0 likes · 11 min read
HyperQ: 64 Qubits Enable 1.1B Model to Surpass 8B Models in Zero-Shot Tasks
Machine Heart
Machine Heart
Oct 23, 2026 · Artificial Intelligence

HyperQ: 64 Qubits Let 1.1B Diffusion Model Outperform 8B Models

HyperQ introduces per-token adaptive quantum circuits via a hypernetwork to augment diffusion language models; with 64 qubits, a 1.1B parameter model surpasses 8B models on six zero-shot tasks, and the quantum circuits are validated on IBM's 156-qubit cluster with minimal performance loss.

HypernetworksIBM quantum clusterZero-Shot Learning
0 likes · 10 min read
HyperQ: 64 Qubits Let 1.1B Diffusion Model Outperform 8B Models
AI Engineering
AI Engineering
Sep 24, 2026 · Artificial Intelligence

CLM-8B: System One Decision Model 9x Faster Than Jev

CLM-8B is a contrastive language model that maps states and actions to a shared vector space for fast decision-making, matching Jev's zero-shot performance on benchmarks like WikiRacing and Super Mario while being 9x faster, and serves as a verifier setting new SOTA on DeepSWE and Terminal-Bench with 4-5x speedup using decoupled encoders and vector caching.

CLM-8BContrastive LearningDecision Model
0 likes · 6 min read
CLM-8B: System One Decision Model 9x Faster Than Jev
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jul 9, 2026 · Artificial Intelligence

How Attending Before Acting Boosts Generalization in Pelican-VLA 0.5

The talk presents Pelican-VLA 0.5, a unified Vision‑Language‑Action model that leverages attention‑level generalization without task‑specific supervision, achieving over 91% success on RoboTwin benchmarks and demonstrating early zero‑shot generalization through a novel Reasoning Slots bottleneck.

Attention GeneralizationEmbodied AIPelican-VLA
0 likes · 6 min read
How Attending Before Acting Boosts Generalization in Pelican-VLA 0.5
Machine Heart
Machine Heart
Jul 9, 2026 · Artificial Intelligence

How DM0.5 Brings Zero‑Shot, Long‑Term Memory, and Robustness to Real‑World VLA

DM0.5 advances the VLA paradigm by adding zero‑shot capability, efficient fine‑tuning, up to 60‑second memory, stronger resistance to visual and human interference, and cross‑robot transfer, achieved through long‑history modeling, embodied reasoning tasks, trajectory‑alignment supervision, and rigorous multi‑source data cleaning pipelines.

Embodied AILong-term MemoryRobotics
0 likes · 13 min read
How DM0.5 Brings Zero‑Shot, Long‑Term Memory, and Robustness to Real‑World VLA
Data Party THU
Data Party THU
May 9, 2026 · Artificial Intelligence

NOSE: Enabling AI to Smell with a Unified Molecule‑Receptor‑Semantic Tri‑modal Representation

NOSE introduces a neural olfactory‑semantic embedding that unifies molecular structure, receptor sequences, and natural‑language odor descriptions into a continuous space, achieving state‑of‑the‑art results on eleven tasks and strong zero‑shot generalization for odor and receptor retrieval.

Contrastive LearningZero-Shot Learningdeep learning
0 likes · 8 min read
NOSE: Enabling AI to Smell with a Unified Molecule‑Receptor‑Semantic Tri‑modal Representation
Data Party THU
Data Party THU
Mar 25, 2026 · Artificial Intelligence

How Knowledge‑Guided Context Optimization Boosts Zero‑Shot Vision‑Language Models

The article analyzes the Base‑to‑New generalization problem of CLIP‑based visual‑language models, explains why standard prompt tuning (CoOp) forgets base knowledge, and presents the KgCoOp framework that adds a knowledge‑guided loss to keep learned prompts close to hand‑crafted ones, dramatically improving unseen‑class performance while preserving efficiency.

CLIPGeneralizationKnowledge-guided Optimization
0 likes · 12 min read
How Knowledge‑Guided Context Optimization Boosts Zero‑Shot Vision‑Language Models
DeepHub IMBA
DeepHub IMBA
Mar 23, 2026 · Artificial Intelligence

How KgCoOp Uses Knowledge‑Guided Context Optimization to Prevent Prompt Tuning Forgetting

The article analyzes why standard prompt tuning (CoOp) causes catastrophic forgetting in visual‑language models, introduces the KgCoOp framework that adds a knowledge‑guided loss to regularize prompts, and shows through extensive experiments on 11 benchmarks that KgCoOp improves unseen‑class accuracy, harmonic mean, and efficiency while discussing trade‑offs and limitations.

Catastrophic ForgettingKnowledge-guided OptimizationPrompt Tuning
0 likes · 11 min read
How KgCoOp Uses Knowledge‑Guided Context Optimization to Prevent Prompt Tuning Forgetting
AI Algorithm Path
AI Algorithm Path
Feb 17, 2026 · Artificial Intelligence

Why Contrastive Learning Is the Core Foundation of Visual Language Models

The article explains how contrastive learning replaces fixed‑category visual training with a relationship‑based approach, detailing the dual‑encoder architecture, cosine similarity loss, batch scaling, temperature control, zero‑shot capabilities, scalability from web data, and the method's strengths and limitations in modern multimodal AI.

CLIPContrastive LearningZero-Shot Learning
0 likes · 25 min read
Why Contrastive Learning Is the Core Foundation of Visual Language Models
Xiaomi Tech
Xiaomi Tech
Feb 5, 2026 · Artificial Intelligence

TacRefineNet: A Tactile‑Driven Model for Millimeter‑Precision Robotic Grasp Refinement

TacRefineNet leverages high‑resolution tactile sensors, multimodal fusion of fingertip touch and proprioception, and a goal‑conditioned refinement network to achieve millimeter‑level grasp adjustments without vision or 3D models, demonstrating zero‑shot deployment and robust generalization across diverse automotive‑factory parts in both simulation and real‑world tests.

Sim-to-RealZero-Shot Learninggrasp refinement
0 likes · 8 min read
TacRefineNet: A Tactile‑Driven Model for Millimeter‑Precision Robotic Grasp Refinement
KooFE Frontend Team
KooFE Frontend Team
Dec 13, 2025 · Artificial Intelligence

Unlocking LLM Reasoning: Advanced Chain‑of‑Thought Prompting Techniques Explained

This article explains how Chain‑of‑Thought prompting and its variants—zero‑shot CoT, Thread of Thought, Tabular CoT, Analogical Prompting, and Step‑back Prompting—enable large language models to perform multi‑step reasoning by breaking problems into intermediate steps, with practical prompts, examples, and implementation details.

Zero-Shot Learningchain-of-thoughtreasoning
0 likes · 12 min read
Unlocking LLM Reasoning: Advanced Chain‑of‑Thought Prompting Techniques Explained
Code Archaeology
Code Archaeology
Oct 13, 2025 · Artificial Intelligence

GPT vs BERT: How In-Context Learning Replaced Fine-Tuning in LLMs

This article traces the evolution from GPT-1's pre-training and fine-tuning paradigm to GPT-3's in-context learning, contrasting GPT's decoder-only generative approach with BERT's encoder-only bidirectional understanding, and explains zero-shot, one-shot, and few-shot learning.

BERTGPTGenerative Pre-training
0 likes · 7 min read
GPT vs BERT: How In-Context Learning Replaced Fine-Tuning in LLMs
Data Party THU
Data Party THU
Aug 10, 2025 · Artificial Intelligence

Can Evolutionary Algorithms Auto-Design Training-Free Vision-Language Model Adaptations?

This study introduces EvoVLMA, an evolutionary vision-language model adaptation framework that automatically searches training-free VLM adaptation algorithms using a two-stage LLM-guided evolution, demonstrating superior performance—such as a 1.91 % accuracy gain on 8-shot image classification—and releasing the code publicly.

Evolutionary AlgorithmsLLMVision-Language Models
0 likes · 5 min read
Can Evolutionary Algorithms Auto-Design Training-Free Vision-Language Model Adaptations?
DataFunTalk
DataFunTalk
Jul 16, 2025 · Artificial Intelligence

How Jason Wei’s Breakthroughs Are Shaping the Future of Large Language Models

Jason Wei, a former Google Brain and OpenAI researcher now at Meta, has driven key advances in large language models—including chain‑of‑thought prompting, instruction tuning, emergent abilities, zero‑shot learning, and data augmentation—shaping both AI research paradigms and real‑world applications.

Chain-of-ThoughtZero-Shot Learningemergent abilities
0 likes · 7 min read
How Jason Wei’s Breakthroughs Are Shaping the Future of Large Language Models
AIWalker
AIWalker
Jun 18, 2025 · Artificial Intelligence

SeNaTra: Nvidia’s Spatial Grouping Layer Pushes Semantic Segmentation Past Swin Transformer

Nvidia introduces SeNaTra, a native‑segmentation vision transformer that replaces uniform down‑sampling with a content‑aware spatial grouping layer, delivering superior zero‑shot and supervised segmentation performance while cutting parameters and FLOPs compared with Swin Transformer and other backbones.

NVIDIAZero-Shot Learningsemantic segmentation
0 likes · 29 min read
SeNaTra: Nvidia’s Spatial Grouping Layer Pushes Semantic Segmentation Past Swin Transformer
DataFunSummit
DataFunSummit
May 23, 2024 · Artificial Intelligence

GraphGPT: Enabling Large Language Models as Zero‑Shot Graph Learners

GraphGPT integrates large language models with graph neural networks by introducing graph tokens and instruction tuning, enabling zero‑shot graph learning for tasks such as node classification and link prediction, and demonstrates superior performance and generalization across supervised and zero‑shot benchmarks.

GraphGPTZero-Shot Learninginstruction tuning
0 likes · 15 min read
GraphGPT: Enabling Large Language Models as Zero‑Shot Graph Learners
NewBeeNLP
NewBeeNLP
Mar 26, 2024 · Artificial Intelligence

How OpenGraph Enables Zero‑Shot Graph Learning Across Datasets

OpenGraph introduces a zero‑shot graph learning framework that unifies graph tokenization, a scalable transformer with efficient sampling, and LLM‑driven data augmentation, achieving superior cross‑dataset generalization on node classification and link prediction tasks, as demonstrated by extensive experiments.

Graph Neural NetworksLLM data augmentationZero-Shot Learning
0 likes · 20 min read
How OpenGraph Enables Zero‑Shot Graph Learning Across Datasets
DataFunTalk
DataFunTalk
Nov 24, 2023 · Artificial Intelligence

Open Vocabulary Detection Contest 2023: Summary of Winning Teams' Technical Solutions

The article reviews the Open Vocabulary Detection Contest organized by the Chinese Society of Image and Graphics and 360 AI Institute, describing the competition setup, dataset characteristics, and detailed winning approaches that combine Detic, CLIP, prompt learning, and multi‑stage pipelines to achieve strong few‑shot and zero‑shot object detection performance.

CLIPCompetitionComputer Vision
0 likes · 17 min read
Open Vocabulary Detection Contest 2023: Summary of Winning Teams' Technical Solutions
DataFunTalk
DataFunTalk
Feb 16, 2023 · Artificial Intelligence

Fine‑Grained Entity Recognition in Tencent TexSmart: System Overview and Key Techniques

This article presents an in‑depth overview of Tencent's TexSmart natural‑language understanding system, highlighting its fine‑grained NER capabilities, knowledge‑base combination methods, remote‑supervision via similar entities, multi‑source zero‑shot fusion, experimental results, and practical insights from a recent NLP summit.

Entity TypingFine-grained NERTexSmart
0 likes · 12 min read
Fine‑Grained Entity Recognition in Tencent TexSmart: System Overview and Key Techniques
NetEase Cloud Music Tech Team
NetEase Cloud Music Tech Team
Apr 27, 2022 · Artificial Intelligence

How Model-Agnostic Interest Learning (MAIL) Solves Cold‑Start in Recommender Systems

This paper introduces MAIL, a model‑agnostic dual‑tower framework that uses a zero‑shot learning tower to generate virtual user behaviors for new users and an embedding‑based ranking tower, achieving 13‑15% CTR lift in large‑scale live‑stream recommendation at NetEase Cloud Music.

EmbeddingZero-Shot Learningcold start
0 likes · 33 min read
How Model-Agnostic Interest Learning (MAIL) Solves Cold‑Start in Recommender Systems