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

Mar 30

Submitted by

dkliang

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

H-EmbodVis

Submitted by

JingweiNi

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

·
9 authors

Submitted by

kpzhang996

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference

AlayaLab

Submitted by

Kyudan

Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models

kaist-ai

Submitted by

yawenluo

ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

·
8 authors

Submitted by

che111

MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies

TUM

Technical University of Munich

Submitted by

zjj1233

RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation

Qwen

Submitted by

Lokshaw

Natural-Language Agent Harnesses

·
5 authors

2

Submitted by

Muennighoff

Composer 2 Technical Report

·
55 authors

Submitted by

xishushu

Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models

PekingUniversity

Peking University

2

Submitted by

omersahintas

LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset

KIT-Karlsruhe

Karlsruhe Institute of Technology

3

Submitted by

yuhuanyang

GenMask: Adapting DiT for Segmentation via Direct Mask

·
9 authors

2

Submitted by

Mor-Li

Learning to Commit: Generating Organic Pull Requests via Online Repository Memory

·
5 authors

2

Submitted by

richardyoung

Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?

·
1 authors

Submitted by

Q-bert

Diffutron: A Masked Diffusion Language Model for Turkish Language

diffutron

2