HuggingFace
FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching
Tool-based image editing (image retouching) is commonly formulated with autoregressive multimodal large language mode...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Nereus: Adaptive Parallelism for LLM Post-Training
Reinforcement learning (RL) post-training for large language models (LLMs) coordinates multiple models across generat...
HuggingFace
Relic: From Multi-Agent Collaboration to Persistent Organizational Capability
Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a reposi...
HuggingFace
Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL
Reinforcement learning (RL) for code agents often uses executable tests to provide binary rewards. With these rewards...
HuggingFace
BoundInk: Boundary-Aware Online Handwriting Generation
Realistic online handwriting depends not only on individual character shapes, but also on how a writer connects, spac...
HuggingFace
Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
A main promise of looped language models is depth-adaptive inference. By looping a block of shared layers a variable ...
HuggingFace
Evidence-Grounded Auditing of Identification Assumptions in Climate-Policy Causal Evaluations
Difference-in-differences (DID) studies are widely used to evaluate climate policy, but assessing the evidence suppor...
HuggingFace
VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models
Pretrained vision-language-action (VLA) models enable broad manipulation but remain unreliable in tasks demanding pre...
HuggingFace
MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation (MOPD) integrates specialized capabilities into a single student, but existing p...
HuggingFace
CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding
Public software repositories, like GitHub and Software Heritage Archive, store billions of files, yet extracting thei...
HuggingFace
Softmax Reparameterization for Output-Head Quantization
Large vocabularies make output heads a substantial inference cost in small language models. We propose softmax repara...
HuggingFace
SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We a...