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 7

Submitted by

andrewzh

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

·
11 authors

Submitted by

CodeGoat24

Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning

·
7 authors

Submitted by

SmerkyG

RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale

·
4 authors

1

Submitted by

shiyi0408

FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios

·
5 authors

Submitted by

iofu728

RetroInfer: A Vector-Storage Approach for Scalable Long-Context LLM Inference

·
18 authors

Submitted by

Xingyu-Zheng

An Empirical Study of Qwen3 Quantization

·
10 authors

Submitted by

Homie0609

Multi-Agent System for Comprehensive Soccer Understanding

·
6 authors

Submitted by

scaperex

Decoding Open-Ended Information Seeking Goals from Eye Movements in Reading

·
4 authors

Submitted by

Marblueocean

HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation

·
6 authors

Submitted by

kevinr

Geospatial Mechanistic Interpretability of Large Language Models

·
3 authors

Submitted by

john-b-yang

SWE-smith: Scaling Data for Software Engineering Agents

·
10 authors

1

Submitted by

shenyunhang

VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model

·
14 authors

Submitted by

Kevin355

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems

·
11 authors

Submitted by

LuLing

Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation

·
10 authors

1

Submitted by

Franck-Dernoncourt

InfoVids: Reimagining the Viewer Experience with Alternative Visualization-Presenter Relationships

·
10 authors

Submitted by

mattf1n

Teaching Models to Understand (but not Generate) High-risk Data

·
5 authors

1

Submitted by

Robot2050

Invoke Interfaces Only When Needed: Adaptive Invocation for Large Language Models in Question Answering

·
3 authors

1

Submitted by

lorashen

Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant

·
2 authors

Submitted by

dnoever

Alpha Excel Benchmark

·
2 authors