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

Oct 28

Submitted by

phython96

ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting

·
7 authors

Submitted by

Avihu

Continuous Speech Synthesis using per-token Latent Diffusion

·
7 authors

Submitted by

akhaliq

FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

·
7 authors

Submitted by

yuexiang96

Teach Multimodal LLMs to Comprehend Electrocardiographic Images

·
4 authors

Submitted by

ldwang

Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data

·
19 authors

Submitted by

Sreyan88

MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark

·
9 authors

Submitted by

CCCCRS

Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design

·
7 authors

Submitted by

omer6nahum

Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance

·
5 authors

Submitted by

Wyattz23

Counting Ability of Large Language Models and Impact of Tokenization

·
3 authors

Submitted by

ljvmiranda921

Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback

·
9 authors

Submitted by

yujianll

Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning

·
4 authors

Submitted by

yuzhaouoe

Analysing the Residual Stream of Language Models Under Knowledge Conflicts

·
9 authors

Submitted by

Mingtongz

Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling

·
3 authors

Submitted by

LingyuLi

Reflection-Bench: probing AI intelligence with reflection

·
7 authors

Submitted by

sergioburdisso

Mapping the Media Landscape: Predicting Factual Reporting and Political Bias Through Web Interactions

·
4 authors

Submitted by

Ksgk-fy

Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration

·
4 authors