HuggingFace
A Zeroth-Order Paradigm for LLM Preference Alignment
Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences beca...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
Action tokenizers play a central role in autoregressive vision-language-action (VLA) models, determining both the tar...
HuggingFace
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization
Recently, linear attention layers have been increasingly adopted to replace softmax attention at scale for long-conte...
HuggingFace
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents
Reliable confidence estimation is increasingly central to the trustworthy deployment of language models: a calibrated...
HuggingFace
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to est...
HuggingFace
Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training
Training a Mixture-of-Experts (MoE) model at long context or large batch size fails as soon as any one component's pe...
HuggingFace
PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
Intelligent systems that act in the world require image understanding that is both comprehensive and spatially ground...
HuggingFace
Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?
This paper reports experiments across six frontier model types from OpenAI, Anthropic, xAI, and Google DeepMind. Ten ...
HuggingFace
Convergent Emergence of In-Context Learning Across Modalities
Few-shot in-context learning (ICL), the capacity of a model to infer abstract patterns from input-output examples pro...
HuggingFace
ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals
Language model-generated rubrics are increasingly used as reward signals for rubric-based reinforcement learning, LLM...
HuggingFace
OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning
Unified multimodal large language models (MLLMs) and multi-agent systems have advanced visual generation. However, th...
HuggingFace
Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement
When we speak of recursive self-improvement (RSI), are we speaking of a phenomenon, a mechanism, or a prospect? Towar...