HuggingFace
AI for Games in the Foundation Model Era
Foundation models, alongside advances in learned game-world models, are reshaping AI across the game lifecycle. Beyon...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Disentangling Representation Evolution in Transformers through Directional Decomposition
Transformer representations evolve through learned additive transformations that either preserve their current direct...
HuggingFace
Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
As language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for...
HuggingFace
Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation
Specialist distillation effectively transfers domain expertise to student models via teacher-generated reasoning traj...
HuggingFace
Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models
Fine-tuning instruct models often improves target performance while inducing behavioral drift from the reference mode...
HuggingFace
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
Interactive control for video generation is moving from coarse prompts toward fine-grained, physically meaningful man...
HuggingFace
Modality-Autoregressive World-Action Models
World-action models (WAMs) jointly model future observations and actions, typically predicting the future as RGB imag...
HuggingFace
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that impr...
HuggingFace
Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems
As AI agents move from bounded tasks to persistent deployments, failures can propagate through memory, tools, other a...
HuggingFace
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a tech...
HuggingFace
StepAudio 3 Music Technical Report
We introduce StepAudio 3 Music, a large-scale, long-form music generation model that supports explicit musical planni...
HuggingFace
StepAudio 3 Realtime Technical Report
Realtime spoken interaction demands deep reasoning, prompt responses, and fluid turn-taking. We present StepAudio 3 R...