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

Mar 31

Submitted by

itaynakash

AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation

·
5 authors

2

Submitted by

Swtheking

Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback

·
8 authors

2

Submitted by

KID-22

Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation

·
8 authors

2

Submitted by

Xiaoye08

A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond

·
18 authors

3

Submitted by

Sonia755

OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning

·
6 authors

Submitted by

daehyeonchoi

ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation

·
5 authors

3

Submitted by

hamzzi

ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback

·
7 authors

3

Submitted by

FrozenBurning

Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency

·
10 authors

2

Submitted by

Chae-Yeon

Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics

·
6 authors

3

Submitted by

yilunzhao

PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving

·
7 authors

2

Submitted by

nielsr

Your ViT is Secretly an Image Segmentation Model

·
8 authors

Submitted by

akhaliq

Segment Any Motion in Videos

·
7 authors

Submitted by

akhaliq

Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging

·
8 authors

Submitted by

louisowen6

A Refined Analysis of Massive Activations in LLMs

·
4 authors

2

Submitted by

bing-li-ai

4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding

·
11 authors

3

Submitted by

Lp256

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

·
9 authors

2

Submitted by

jhpark96

Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion Model

·
3 authors

2

Submitted by

IsshikiHugh

Reconstructing Humans with a Biomechanically Accurate Skeleton

·
5 authors

2

Submitted by

ZiyueWang

MedAgent-Pro: Towards Multi-modal Evidence-based Medical Diagnosis via Reasoning Agentic Workflow

·
4 authors

2

Submitted by

altndrr

On Large Multimodal Models as Open-World Image Classifiers

·
6 authors

2

Submitted by

vortex778

X^{2}-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction

·
6 authors

2

Submitted by

minimario

Challenges and Paths Towards AI for Software Engineering

·
10 authors

2

Submitted by

yuweiyin

SWI: Speaking with Intent in Large Language Models

·
3 authors

2