Accepted Papers

1. Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models
2. Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures
3. Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)
4. On the Feasibility of In-Context Probing for Data Attribution
5. Energy Considerations of Large Language Model Inference and Efficiency Optimizations
6. AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
7. Human-Aligned Chess With a Bit of Search
8. Fairshare Data Pricing for Large Language Models
9. Social Scaffolds: A Generalization Framework for Social Understanding Tasks
10. MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools
11. Should I Agree with You? Simulating Persuasion and Decision Dynamics in Multi-Agent Moral Dilemmas
12. Can KBQA Models Predict Their Reasoning Paths? Isomorphism Prediction Task as a Proxy
13. Can Long-Context Language Models Solve Repository-Level Code Generation?
14. Exploring the Separation of Structural and Semantic Representations in Symbolic Knowledge within LLMs
15. Programming with Pixels: Towards Generalist Software Engineering Agents
16. Human-Centered Evaluation of Expressed Confidence in Machine Translation
17. Leveraging Machine-generated Rationales for Conversational Forecasting
18. Loki: Studying MARL Collusion using LLMs in a Kuhn Poker Environment