arXiv
ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize
Evolutionary prompt optimizers such as GEPA suffer from prompt bloat: each iteration appends rules and caveats, produ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints
Language-model judges now gate training data, score generations, and drive leaderboards. The judge is then a measurem...
arXiv
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remot...
HuggingFace
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, execut...
HuggingFace
Principia: Relational Physics Tests for Video Models
Evaluating physical reasoning in video models is difficult because absolute motion measurements depend on frame rate,...
HuggingFace
Environment Evolution for Terminal Agents
Scaling interactive and verifiable environments is critical for training terminal agents. As frontier models become m...
HuggingFace
Editable Visual Design
While diffusion base models such as GPT-Image-2 and Nano-Banana exhibit remarkable visual expressiveness, their end-t...
HuggingFace
CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation
MLLM-based embedding models remain limited in compositional retrieval, often failing to distinguish scenes containing...
HuggingFace
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. E...
HuggingFace
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Large language models achieve superior performance on tasks that require extended reasoning, but long chains of thoug...
HuggingFace
WorldReward: Reward Modeling for Camera-Conditioned World Models
Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected sce...
HuggingFace
FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow
We present FlashRender, a few-step generative rendering framework that retakes a source video along a target camera t...