GeezerVison

When Demonstrations Fail: Diagnosing the Limits of In-Context Learning in Large Audio-Language Models with Progressive Cue Removal

[Findings of EMNLP 26] ICICLE: Expanding Retrieval with In-Context Documents

Tracking Evolving Needs: \\Discovering and Naming Dynamic Intents in Customer Service Dialogues

When Users Don’t Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents

From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers

AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning

A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories