Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing Fal…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models
Dynamic Heterogeneous Graph Representation Learning: A Survey
Building a research-software catalog with a coding agent: from hackathon prototype to pub…
Persistent Teacher Anchoring for Tool-Using Agents
VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition
Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Soft…
Enhancing Multimodal Emotion Recognition via Multi-Feature Encoding and Attention-Based F…
Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters
Hakken: Predicting future discoveries to fill the gaps in today's knowledge
Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection
A Removal Based Approach to Improve LLM Faithfulness at Test-Time
A Roadmap for MEG Foundation Models
Gradient-based Model Shortcut Detection for Time Series Classification
Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language…
A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual …
Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Th…
Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics
Scalable Context Orchestration for Serving LLMs Over Voice
Evidence Integration in Large Language Models
Abstraction Agent
What Moves? Localized Motion Representations for Compositional Scene Control
Training-Free Halving of Activated Experts in Fine-Grained Mixture-of-Experts Models
Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence
A Deep Generative Model for Synthesizing Labeled Wireless Signals
AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks
When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Conc…
Substrate-Aware AI Agents: Execution Context as a First-Class Input
Do LLMs Exhibit Coherent Knowledge Structures in Mathematical Reasoning? A Perspective fr…