HuggingFace
Self-Play Search Distillation for Large Language Model Reasoning
Improving reasoning abilities in Large Language Models (LLMs) requires high-quality data that exposes difficult decis...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Selecting Diverse SFT Traces Improves Post-RL Generalization
Verified solutions are not equally useful for preparing reasoning models for reinforcement learning (RL). We present ...
HuggingFace
LeRF: Learning Reference Coordinate Frames for Perspective Taking Reasoning
Perspective taking is a fundamental component of spatial intelligence, requiring models interpret spatial relations f...
HuggingFace
CineSubBench: Evaluating LLMs on Long-Form Narrative and Cultural Understanding from Multilingual Movie Subtitles
Large language models are increasingly evaluated in specialized domains such as law, medicine, software engineering, ...
HuggingFace
Approximating Softmax in Pretrained LLMs: Model Sensitivity and Kernel Acceleration
On NVIDIA Blackwell B200, tensor-core throughput outpaces special-function exponential throughput by more than two or...
arXiv
Reasoning with Continuous Latent Diffusion
Continuous diffusion generates complete reasoning solutions through iterative refinement in latent space. We introduc...
arXiv
Distillation Defenses Easily Break After Reinforcement Learning
Distillation attacks copy the reasoning capabilities of closed-source large language models, allowing bad actors to r...
arXiv
A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion
Reliable deployment of graph neural networks requires calibration, out-of-distribution (OOD) detection, and robustnes...
arXiv
Reinforcing Agentic Creativity in Scientific Ideation with Night Science
Large language models (LLMs) excel at structured, verifiable tasks, but their low-entropy bias can produce homogeneou...
arXiv
X-Reset: Scaling Object-Centric Reinforcement Learning via Cross-Embodiment Resets
Reinforcement learning (RL) in simulation can train dexterous manipulation policies without robot demonstrations, but...
arXiv
Failure-Transparent Agents: Benchmarking Post-Failure Reporting in Tool-Using Language Models
Tool-using agents can fail twice: a required tool can fail, and the agent can then report success without the evidenc...
arXiv
Shockingly Simple Self-retrospection Improves Agentic Models Without RL
People learn not only by repeating successful actions, but also by recounting and explaining their experiences, revis...