new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

by AK and the research community

Jul 10

Submitted by

taesiri

Vision language models are blind

·
4 authors

Submitted by

ari9dam

AgentInstruct: Toward Generative Teaching with Agentic Flows

·
14 authors

Submitted by

akhaliq

Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence

·
10 authors

Submitted by

orrzohar

Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision

·
5 authors

Submitted by

akhaliq

RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models

·
9 authors

Submitted by

Shaltiel

Adapting LLMs to Hebrew: Unveiling DictaLM 2.0 with Enhanced Vocabulary and Instruction Capabilities

·
4 authors

Submitted by

akhaliq

MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions

·
9 authors

Submitted by

RickyDeSkywalker

TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts

·
7 authors

Submitted by

xhluca

BM25S: Orders of magnitude faster lexical search via eager sparse scoring

·
1 authors

Submitted by

fredzzhang

Knowledge Composition using Task Vectors with Learned Anisotropic Scaling

·
5 authors

Submitted by

voidism

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

·
6 authors

Submitted by

KBlueLeaf

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions

·
10 authors

Submitted by

akhaliq

VIMI: Grounding Video Generation through Multi-modal Instruction

·
8 authors

Submitted by

Mivg

From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty

·
4 authors

Submitted by

nikolamilosevic

How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questions

·
6 authors

Submitted by

rachneetkaur

LETS-C: Leveraging Language Embedding for Time Series Classification

·
4 authors