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

Nov 10

Submitted by

Zihao1

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

tencent

Submitted by

taesiri

Visual Spatial Tuning

ByteDance-Seed

Submitted by

taesiri

DeepEyesV2: Toward Agentic Multimodal Model

rednote-hilab

Submitted by

AnnieFeng

VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks

AWS

Amazon Web Services

Submitted by

ProKil

Real-Time Reasoning Agents in Evolving Environments

SALT-NLP

Social And Language Technology Lab

Submitted by

taesiri

Dense Motion Captioning

·
4 authors

Submitted by

taesiri

Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings

·
8 authors

Submitted by

taesiri

Jailbreaking in the Haystack

·
6 authors

Submitted by

hao-li

HAFixAgent: History-Aware Automated Program Repair Agent

·
4 authors

2

Submitted by

JiayuJeff

CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?

·
10 authors