HuggingFace
HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
Embodied navigation requires agents to interpret visual observations, accumulate spatial knowledge, and execute actio...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, e...
HuggingFace
ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMs
A radiology report can already answer a clinical question, so it is hard to tell whether a vision-language model also...
HuggingFace
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus
Orthrus is a hybrid autoregressive-diffusion architecture that accelerates autoregressive language-model inference by...
HuggingFace
Learning Sparse Decision Trees via Transformer Variational Auto-Encoders
Decision trees are among the most widely used models in machine learning, largely due to their transparent decision l...
HuggingFace
Thought without systematicity? Evaluating reasoning models on rule induction tasks
A central tenet of human cognition is systematicity, the principle that understanding one concept is inherently tied ...
HuggingFace
E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning
Can financial vision-language models (VLMs) turn chart evidence into reliable action recommendations? Existing halluc...
HuggingFace
Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures
The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures withi...
HuggingFace
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up
We demonstrate that training LLMs with RL does not improve performance equally across a dataset. RL shows large impro...
HuggingFace
Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition
A core goal of efficient reasoning is to improve the accuracy-efficiency frontier. However, jointly improving reasoni...
arXiv
Per-Matrix Optimality Is Not Enough: Three-Level Optimization for Low-Rank LLM Compression
Per-matrix singular value decomposition (SVD) truncation is Eckart-Young optimal in the whitened Frobenius norm, but ...
arXiv
Before You Poll with LLMs: A Deliberative Diagnostic Framework
Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for...