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 9

Submitted by

ridger

A Survey on Latent Reasoning

·
33 authors

Submitted by

judge

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents

·
16 authors

Submitted by

tytyt

OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion

·
10 authors

Submitted by

happzy2633

CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization

·
19 authors

Submitted by

wangrongsheng

MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos

·
7 authors

Submitted by

taiwang

StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling

·
12 authors

Submitted by

zsytony

Coding Triangle: How Does Large Language Model Understand Code?

·
6 authors

Submitted by

HelloKKMe

GTA1: GUI Test-time Scaling Agent

·
14 authors

Submitted by

songtingyu

Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers

·
5 authors

Submitted by

yxlu0

Is Diversity All You Need for Scalable Robotic Manipulation?

·
10 authors

Submitted by

songdj

SAMed-2: Selective Memory Enhanced Medical Segment Anything Model

·
14 authors

Submitted by

acharkq

PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs

·
12 authors

Submitted by

melhoushi

any4: Learned 4-bit Numeric Representation for LLMs

·
2 authors

Submitted by

xhluca

How to Train Your LLM Web Agent: A Statistical Diagnosis

·
16 authors

Submitted by

BestWishYsh

Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation

·
5 authors

Submitted by

Xuandong

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation

·
4 authors

Submitted by

ZetangForward

LOOM-Scope: a comprehensive and efficient LOng-cOntext Model evaluation framework

·
8 authors

Submitted by

xinyu1205

High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning

·
6 authors