HuggingFace
YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family
Generic parameter-efficient fine-tuning (PEFT) methods transferred from language models can fail silently on real-tim...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors
Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it a...
HuggingFace
PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. ...
HuggingFace
Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning
Audio reasoning is essential for machine understanding of the acoustic world. Reinforcement learning with verifiable ...
HuggingFace
Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events
Personality-conditioned LLM agents (PC-Agents) are increasingly used in emotional support, social simulation, and rol...
HuggingFace
Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding
Creative capabilities of MLLMs matter in design, communication, education, and human--AI collaboration, yet remain di...
HuggingFace
SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs
Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) exhibit fundamentally different behaviors in enhancing m...
HuggingFace
Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning
Recent works train agents by constructing large-scale multimodal environment pools. However, we find that simply incr...
HuggingFace
Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination
Test data from public benchmarks inevitably leaks into pretraining corpora, inflating evaluation scores once memorize...
HuggingFace
Towards Interpretable Foundation Models for Retinal Fundus Images
Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically vi...
HuggingFace
Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence
Vision-language models are increasingly serving as the reasoning core of embodied agents. Robot execution is inherent...
HuggingFace
OneEmo: A Unified Multimodal Reasoning Model for Emotion Perception, Understanding, and Interaction
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in emotional intelligence. However...