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 11

Submitted by

msalnikov

Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models

·
10 authors

1

Submitted by

myownskyW7

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better

·
7 authors

Submitted by

zlzheng

RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling

·
3 authors

1

Submitted by

lupantech

Solving Inequality Proofs with Large Language Models

·
7 authors

Submitted by

gdhe17

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

·
5 authors

1

Submitted by

aadarsh99

Aligning Text, Images, and 3D Structure Token-by-Token

·
3 authors

Submitted by

xhyandwyy

Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation

·
12 authors

1

Submitted by

agwmon

Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models

·
7 authors

Submitted by

deepkyu

Seeing Voices: Generating A-Roll Video from Audio with Mirage

·
13 authors

1

Submitted by

yeonseokjeong

ECoRAG: Evidentiality-guided Compression for Long Context RAG

·
4 authors

1

Submitted by

rishitdagli

Squeeze3D: Your 3D Generation Model is Secretly an Extreme Neural Compressor

·
5 authors

2

Submitted by

fanqiNO1

Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs

·
8 authors

1

Submitted by

lunar677

DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval

·
9 authors

2

Submitted by

cattana

DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs

·
9 authors

Submitted by

stefan-it

Institutional Books 1.0: A 242B token dataset from Harvard Library's collections, refined for accuracy and usability

·
11 authors

Submitted by

JackBAI

Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction

·
11 authors

1

Submitted by

cajie

MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models

·
9 authors

1

Submitted by

YanAdjeNole

RKEFino1: A Regulation Knowledge-Enhanced Large Language Model

·
4 authors

1

Submitted by

Jianyuan1

Mathesis: Towards Formal Theorem Proving from Natural Languages

·
20 authors

2

Submitted by

skyil7

MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Models

·
3 authors

1

Submitted by

lizhuang144

QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answering

·
4 authors