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

Feb 17

Submitted by

akhaliq

Large Language Diffusion Models

·
10 authors

9

Submitted by

AlexCuadron

The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

·
16 authors

2

Submitted by

turrf

Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model

·
115 authors

Submitted by

Yif29

Region-Adaptive Sampling for Diffusion Transformers

·
7 authors

3

Submitted by

taesiri

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

·
23 authors

Submitted by

yifanzhang114

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

·
20 authors

5

Submitted by

rinong

ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation

·
4 authors

Submitted by

akhaliq

Diverse Inference and Verification for Advanced Reasoning

·
14 authors

Submitted by

Shengkun

DarwinLM: Evolutionary Structured Pruning of Large Language Models

·
5 authors

7

Submitted by

deqing

FoNE: Precise Single-Token Number Embeddings via Fourier Features

·
5 authors

3

Submitted by

lukasz-staniszewski

Precise Parameter Localization for Textual Generation in Diffusion Models

·
5 authors

2

Submitted by

gsarti

We Can't Understand AI Using our Existing Vocabulary

·
3 authors

Submitted by

abenechehab

AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting

·
6 authors

2

Submitted by

DGurgurov

Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages

·
4 authors

2

Submitted by

Asaf-Yehudai

Selective Self-to-Supervised Fine-Tuning for Generalization in Large Language Models

·
6 authors

2

Submitted by

xuxw98

Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding

·
6 authors

Submitted by

SP4595

STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning

·
7 authors

2

Submitted by

nielsr

Cluster and Predict Latents Patches for Improved Masked Image Modeling

·
5 authors

Submitted by

z-hb

MRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers

·
6 authors

Submitted by

akhaliq

CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages

·
10 authors

Submitted by

cmhungsteve

V2V-LLM: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multi-Modal Large Language Models

·
6 authors

3

Submitted by

akhaliq

Jailbreaking to Jailbreak

·
10 authors

Submitted by

mjbuehler

Agentic End-to-End De Novo Protein Design for Tailored Dynamics Using a Language Diffusion Model

·
2 authors