HuggingFace
CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation
On-policy knowledge distillation transfers reasoning from large teachers to compact students, but existing approaches...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Memory for Large Language Models
Memory has evolved into a foundational architectural dimension in large language models (LLMs), shifting from an impl...
HuggingFace
πR^2: Reactive Real-time Flow Policies
Generalist manipulation policies increasingly take the form of action-chunking flow policies built on large pretraine...
HuggingFace
Voice Memory for Agentic Speech Recognition
We present Voice Memory, a inference-only scheme for agentic speech recognition: at stream time, a frozen corrector r...
HuggingFace
DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation
Existing autoregressive video distillation methods commonly adopt a Distribution Matching Distillation (DMD)-based mu...
HuggingFace
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including ...
HuggingFace
SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch
LLM-based agents excel at software engineering tasks where an existing codebase provides context, but constructing a ...
arXiv
On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment
Fine-tuning is the dominant paradigm for specializing large language models (LLMs), yet it exposes a critical vulnera...
arXiv
Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents
As LLM agents increasingly depend on diverse external services such as search engines, databases, and connectors, age...
arXiv
SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context
Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and ...
arXiv
MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning
With the development of audio large language models (AudioLLMs), audio captioning needs to move from brief descriptio...
arXiv
AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching
Ontology matching (OM) has traditionally been formulated as either equivalence discovery or subsumption matching. The...