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

Aug 8

Submitted by

Liang0223

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

·
10 authors

Submitted by

ChengsongHuang

R-Zero: Self-Evolving Reasoning LLM from Zero Data

·
9 authors

Submitted by

sundrops

Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

·
14 authors

Submitted by

tellarin

DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

·
10 authors

Submitted by

ZhangYuhan

Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

·
8 authors

3

Submitted by

shuaishuaicdp

Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?

·
7 authors

Submitted by

Bohan-Jiang

Are Today's LLMs Ready to Explain Well-Being Concepts?

·
5 authors

Submitted by

WhiteCatY

Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability

·
5 authors

Submitted by

linxinso

CoAct-1: Computer-using Agents with Coding as Actions

·
12 authors

3

Submitted by

ChenyangLyu

Marco-Voice Technical Report

·
11 authors

Submitted by

amazingj

Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

·
7 authors

2

Submitted by

yichaodu

Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models

·
11 authors

Submitted by

SiriusL

InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

·
7 authors

Submitted by

HenghuiDing

MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

·
8 authors

Submitted by

ChengmingX

StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

·
9 authors

Submitted by

ccsasuke

Learning to Reason for Factuality

·
8 authors

Submitted by

yxl66666

Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling

·
9 authors

Submitted by

amanchadha

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

·
6 authors

2

Submitted by

ZhengChen1999

Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

·
6 authors

Submitted by

mnandwana

REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation

·
4 authors

Submitted by

amanchadha

I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations

·
4 authors

2

Submitted by

reshmighosh

Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

·
10 authors

2

Submitted by

fengyiwu

RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation

·
7 authors

Submitted by

liuziyan

I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking

·
9 authors

Submitted by

Zihao1

Attention Basin: Why Contextual Position Matters in Large Language Models

·
9 authors

Submitted by

nielsr

Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decode

·
5 authors