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 5

Submitted by

Hila

VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models

·
8 authors

Submitted by

akhaliq

ACECODER: Acing Coder RL via Automated Test-Case Synthesis

·
6 authors

Submitted by

ngushchin

Inverse Bridge Matching Distillation

·
6 authors

Submitted by

chaoscodes

Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search

·
10 authors

Submitted by

DaYin

QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search

·
7 authors

Submitted by

Dominic789654

Can LLMs Maintain Fundamental Abilities under KV Cache Compression?

·
9 authors

Submitted by

codelion

Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?

·
4 authors

Submitted by

dahyekim

Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations

·
2 authors

Submitted by

ShizhaoSun

Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models

·
4 authors

Submitted by

xdeng77

COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation

·
8 authors

Submitted by

nupurkmr9

Generating Multi-Image Synthetic Data for Text-to-Image Customization

·
5 authors

Submitted by

ericzhao28

Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification

·
3 authors

Submitted by

wenzhifang

Federated Sketching LoRA: On-Device Collaborative Fine-Tuning of Large Language Models

·
5 authors

Submitted by

ttttonyhe

Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense

·
10 authors