arXiv
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e.,...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own co...
arXiv
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of action...
arXiv
Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision
When does training language models (LMs) to generate explanations of their predictions yield faithful introspection, ...
HuggingFace
DOPD: Dual On-policy Distillation
On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense...
HuggingFace
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture? Lar...
HuggingFace
AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation
Audio-video generation has recently gained unprecedented research attention, aiming to synthesize high-quality soundi...
HuggingFace
Orca: The World is in Your Mind
We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent s...
HuggingFace
MemLearner: Learning to Query Context memory for Video World Models
Video World Models are interactive video generation models that predict future world states based on user actions and...
HuggingFace
PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation
Autoregressive Transformers dominate high-quality mesh generation by producing artist-worthy topologies, yet their in...
HuggingFace
Xiaomi-GUI-0 Technical Report
Graphical user interface (GUI) agents build on vision-language models to complete user tasks end-to-end in real appli...
HuggingFace
BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
Speculative decoding accelerates inference by using a lightweight draft model to generate candidate tokens in paralle...