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

Apr 28

Submitted by

syCen

Towards Understanding Camera Motions in Any Video

·
15 authors

2

Submitted by

xuchensong

Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning

·
13 authors

2

Submitted by

hongyuw

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

·
3 authors

2

Submitted by

YunxinLi

VideoVista-CulturalLingo: 360^circ Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension

·
7 authors

2

Submitted by

HanleiZhang

Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark

·
8 authors

2

Submitted by

alemiaschi

Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation

·
9 authors

Submitted by

pnawrot

The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs

·
6 authors

3

Submitted by

carpedkm

Subject-driven Video Generation via Disentangled Identity and Motion

·
7 authors

2

Submitted by

xutan

Kimi-Audio Technical Report

·
40 authors

2

Submitted by

amazingj

DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models

·
7 authors

2

Submitted by

zaplm

DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency

·
7 authors

2

Submitted by

Pclanglais

Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family

·
9 authors

2