Cross-modal Steering Vectors Exist Across Both Image and Text Generation
Paper • 2610.36269 • Published • 12
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Cross-modal Steering Vectors Exist Across Both Image and Text Generation
Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs
BennoKrojer
submitted a
paper to Daily Papers 6 days ago
AHHHZ
authored a
paper 19 days ago
artemZholus
submitted a
paper to Daily Papers 26 days ago
jcblaise
authored 3
papers 29 days ago
FilBench: Can LLMs Understand and Generate Filipino?
Paper • 2508.03523 • Published • 1
Idea First, Code Later: Disentangling Problem Solving from Code Generation in Evaluating LLMs for Competitive Programming
Paper • 2601.11332 • Published • 1
HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents
Paper • 2610.03574 • Published • 22
lucadellalib
authored a
paper about 2 months ago
zpointsun
authored 3
papers 3 months ago
Training Diffusion Language Models for Black-Box Optimization
Paper • 2603.17919 • Published • 15
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Paper • 2607.13431 • Published • 15
Beyond Message Passing: A Semantic View of Agent Communication Protocols
Paper • 2604.02369 • Published • 1
arkilpatel
submitted a
paper to Daily Papers 4 months ago
ludolara
authored 2
papers 5 months ago
Louieworth
submitted a
paper to Daily Papers 5 months ago
haolun-wu
authored 6
papers 6 months ago
Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning
Paper • 2511.07784 • Published
PartnerMAS: An LLM Hierarchical Multi-Agent Framework for Business Partner Selection on High-Dimensional Features
Paper • 2509.24046 • Published
Logits are All We Need to Adapt Closed Models
Paper • 2502.06806 • Published
LLM Use for Mental Health: Crowdsourcing Users' Sentiment-based Perspectives and Values from Social Discussions
Paper • 2512.07797 • Published
"I use ChatGPT to humanize my words": Affordances and Risks of ChatGPT to Autistic Users
Paper • 2601.17946 • Published
LLM Safety From Within: Detecting Harmful Content with Internal Representations
Paper • 2604.18519 • Published • 21