HuggingFace
Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL
Reinforcement learning (RL) has emerged as a powerful approach for improving reasoning in language and vision-languag...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Temporal Multi-Signal Fusion for Token-Level Hallucination Detection
Token-level hallucination detectors score each token independently from a single signal, and fail exactly when the ge...
HuggingFace
The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning
Popular facts are memorised more deeply during pretraining and resist removal longer than rare ones, yet existing LLM...
HuggingFace
SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents
Agent frameworks increasingly package procedural knowledge as skills: instruction files an agent reads on demand, whi...
HuggingFace
CardioState-JEPA: Delay-Aware Cross-Modal Learning of a Shared Cardiac Representation
Electrocardiography (ECG), photoplethysmography (PPG), and phonocardiography (PCG) provide complementary views of the...
HuggingFace
PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX
We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-speci...
HuggingFace
LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents
Reinforcement learning for coding agents increasingly relies on long-running agent harnesses to manage tool integrati...
HuggingFace
The Problem Is the Problem: Towards Scalable Mathematical Discovery
AI systems are increasingly capable of contributing to mathematical research. In research practice, frontier-model re...
HuggingFace
FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis
Training terminal agents requires scalable executable supervision, yet synthesizing high-quality terminal tasks remai...
arXiv
An Omitted Mode Is a Rare Rule: The Sampling-Verification Danger Law in Continuous Code World Models
In the Code World Model paradigm an LLM synthesizes an executable world model that a classical planner searches, and ...
arXiv
Towards Zero-Shot Task Transfer with Neurosymbolic World Models
State-of-the-art model-based reinforcement learning methods learn neural world models that allow policy improvement b...
arXiv
Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection
Online log anomaly detection is critical for maintaining the reliability of large-scale computing systems. Although r...