arXiv
Interpretable Adaptive Sampling for LLM Test-Time Scaling
Test-time scaling improves LLM reasoning by generating and aggregating multiple candidate answers, yet many pipelines...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Separating quantum circuits from classical LLMs
Modern large language models - transformers and diffusion language models - are built around two canonical algorithmi...
arXiv
Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations
Human input reaches language models by typing or speaking, and each channel leaves a distinct signature: orthographic...
arXiv
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large...
arXiv
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video stream...
arXiv
Can Large Language Models Recover Semantic Optimization Opportunities That Compilers Miss?
Optimizing compilers miss profitable transformations when their enabling semantics are absent from the analyzed progr...
arXiv
Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility
Large language models can solve substantially harder reasoning problems with more inference-time compute. The term "t...
arXiv
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, exi...
HuggingFace
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
Recent advances in image generation have demonstrated the potential of unified multimodal models that integrate under...
HuggingFace
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
Real-time video editing requires low-latency causal generation with bounded computational resources while preserving ...
HuggingFace
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, exi...
HuggingFace
CAPEval: A Decoupled Caption Evaluation across Understanding and Generation
Captions serve as a primary supervision signal for both multimodal understanding and text-to-image generation. Howeve...