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

Feb 24

Submitted by

razzant

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

·
7 authors

Submitted by

Dany-0

SurveyX: Academic Survey Automation via Large Language Models

·
12 authors

Submitted by

DongkiKim

Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model

·
3 authors

Submitted by

wzhgba

MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction

·
6 authors

Submitted by

yiren98

PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data

·
7 authors

Submitted by

akhaliq

SIFT: Grounding LLM Reasoning in Contexts via Stickers

·
4 authors

Submitted by

Sterzhang

VLM$^2$-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues

·
6 authors

Submitted by

Ningyu

LightThinker: Thinking Step-by-Step Compression

·
9 authors

Submitted by

Yeonjun

Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models

·
7 authors

Submitted by

WhiteCatY

StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following

·
5 authors

Submitted by

AdinaY

MoBA: Mixture of Block Attention for Long-Context LLMs

·
25 authors

Submitted by

sangheeeee

Evaluating Multimodal Generative AI with Korean Educational Standards

·
2 authors

Submitted by

heegyu

Towards Fully-Automated Materials Discovery via Large-Scale Synthesis Dataset and Expert-Level LLM-as-a-Judge

·
15 authors

Submitted by

SP2001

MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models

·
7 authors

Submitted by

akhaliq

Think Inside the JSON: Reinforcement Strategy for Strict LLM Schema Adherence

·
3 authors

Submitted by

BestWishYsh

FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation

·
6 authors

Submitted by

ahmedheakl

KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding

·
10 authors

Submitted by

AngxiaoYue

ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation

·
3 authors

Submitted by

akhaliq

InterFeedback: Unveiling Interactive Intelligence of Large Multimodal Models via Human Feedback

·
5 authors

Submitted by

akhaliq

The Relationship Between Reasoning and Performance in Large Language Models -- o3 (mini) Thinks Harder, Not Longer

·
3 authors

Submitted by

pkargupta

Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis

·
4 authors

Submitted by

taesiri

Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?

·
13 authors

Submitted by

akhaliq

One-step Diffusion Models with $f$-Divergence Distribution Matching

·
3 authors

Submitted by

AjayP13

mStyleDistance: Multilingual Style Embeddings and their Evaluation

·
5 authors

Submitted by

kjunh

EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild

·
8 authors

Submitted by

sayandsarkar

CrossOver: 3D Scene Cross-Modal Alignment

·
5 authors

Submitted by

fromthesky

PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference

·
1 authors

Submitted by

oceanusity

Learning to Discover Regulatory Elements for Gene Expression Prediction

·
4 authors

Submitted by

elliotschu

Rare Disease Differential Diagnosis with Large Language Models at Scale: From Abdominal Actinomycosis to Wilson's Disease

·
3 authors

Submitted by

yueqingliang

Benchmarking LLMs for Political Science: A United Nations Perspective

·
9 authors

Submitted by

nielsr

WHAC: World-grounded Humans and Cameras

·
12 authors

Submitted by

circleLZY

JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework

·
6 authors

Submitted by

vaidehi99

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning

·
3 authors

Submitted by

dnoever

Beyond No: Quantifying AI Over-Refusal and Emotional Attachment Boundaries

·
2 authors