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

Jun 30

Submitted by

wjkang

AsyncOPD: How Stale Can On-Policy Distillation Be?

furiosa-ai

Submitted by

sY713

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

InternScience

Submitted by

Jinyang23

TACO: Tool-Augmented Credit Optimization for Agentic Tool Use

·
8 authors

Submitted by

erjui

PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents

kaist-ai

Submitted by

MingLiiii

Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction

·
7 authors

Submitted by

Y-Sisyphus

MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation

·
7 authors

1

Submitted by

jacklishufan

Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis

nvidia

Submitted by

fansunqi

Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction

·
5 authors

Submitted by

haoyou11

Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE

AlibabaTongyiLab

Submitted by

LayneH

How Good Can Linear Models Be for Time-Series Forecasting?

SakanaAI

Submitted by

Bowieee

ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models

·
8 authors

Submitted by

fansunqi

GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots

Tencent-Hunyuan

Tencent Hunyuan