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 30

Submitted by

ai-alanov

CLEAR: Character Unlearning in Textual and Visual Modalities

·
9 authors

Submitted by

zhangysk

AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions

·
14 authors

Submitted by

EthanTaylor

SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization

·
6 authors

Submitted by

ydeng9

Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning

·
2 authors

Submitted by

jiang719

Can Language Models Replace Programmers? REPOCOD Says 'Not Yet'

·
4 authors

Submitted by

wenlinyao

OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization

·
8 authors

Submitted by

jianlanluo

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

·
4 authors

Submitted by

g-luo

Task Vectors are Cross-Modal

·
3 authors

Submitted by

preminstrel

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

·
9 authors

Submitted by

theryanliu

Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse

·
6 authors

Submitted by

cheryyunl

Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Dataset

·
6 authors

Submitted by

voidism

Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback

·
4 authors

Submitted by

fxwang

Accelerating Direct Preference Optimization with Prefix Sharing

·
2 authors

Submitted by

atutej

RARe: Retrieval Augmented Retrieval with In-Context Examples

·
4 authors

Submitted by

iliashum

Measuring memorization through probabilistic discoverable extraction

·
5 authors