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

Jul 27

Submitted by

taesiri

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

QwenBusinessUnit-Edu

QwenBusinessUnit-Edu

Submitted by

lhpku20010120

DataPrep-Bench: Benchmarking LLMs as Training Data Preparators

·
14 authors

Submitted by

taesiri

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

nvidia

Submitted by

taesiri

Scaling Native Multimodal Pre-Training From Scratch

Tencent-Hunyuan

Tencent Hunyuan

Submitted by

hongst

LAMAR: An Open Language-Aware Multilingual Alignment Reranker

nlpai-lab

NLP & AI - Korea University

Submitted by

gdadhich

Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems

·
1 authors

Submitted by

AmirhoseinGH

Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making

huawei technologies co. ltd

Submitted by

soujanyaporia

IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation

declare-lab

Deep Cognition and Language Research (DeCLaRe) Lab

Submitted by

taesiri

SceneActBench: Can Agents Act on the 3D Scenes They See?

·
14 authors

Submitted by

taesiri

Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering

·
4 authors

Submitted by

zpatrick

VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression

·
4 authors