new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

May 29

Submitted by

ganqu

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

·
17 authors

Submitted by

jt-zhang

SageAttention2++: A More Efficient Implementation of SageAttention2

·
8 authors

Submitted by

fuvty

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

·
9 authors

Submitted by

WaltonFuture

Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO

·
7 authors

Submitted by

yushi

DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research

·
11 authors

Submitted by

WaltonFuture

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

·
8 authors

Submitted by

chrisliu298

Skywork Open Reasoner 1 Technical Report

·
17 authors

Submitted by

YangXiao-nlp

LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling

·
7 authors

1

Submitted by

YangXiao-nlp

Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States

·
8 authors

1

Submitted by

callanwu

WebDancer: Towards Autonomous Information Seeking Agency

·
12 authors

3

Submitted by

vyokky

Text2Grad: Reinforcement Learning from Natural Language Feedback

·
8 authors

Submitted by

YuanYuhui

PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models

·
9 authors

Submitted by

NCJ

RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination

·
5 authors

Submitted by

j-min

EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance

·
7 authors

Submitted by

yiren98

GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains

·
5 authors

Submitted by

YuchiWang

RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction

·
9 authors

Submitted by

cqsss

Benchmarking Recommendation, Classification, and Tracing Based on Hugging Face Knowledge Graph

·
6 authors

1

Submitted by

Sugewud

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking

·
9 authors

1

Submitted by

brucelyu

Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese

·
4 authors

Submitted by

ethanchern

Thinking with Generated Images

·
8 authors

Submitted by

yuzhen17

Pitfalls of Rule- and Model-based Verifiers -- A Case Study on Mathematical Reasoning

·
5 authors