2026

• Machine Consciousness blog
• Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks papers
• The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents papers
• Video-Based Reward Modeling for Computer-Use Agents papers
• DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning papers
• Experiential Reinforcement Learning papers
• One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence papers

2025

• STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models papers
• The Hallucination Tax of Reinforcement Finetuning papers
• CoAct-1: Computer-using Agents with Coding as Actions papers
• Efficient Reinforcement Finetuning via Adaptive Curriculum Learning papers
• Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base papers
• On the Trustworthiness of Generative Foundation Models papers
• Detecting and Filtering Unsafe Training Data via Data Attribution papers

2024

• WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback papers
• How Susceptible are Large Language Models to Ideological Manipulation? papers

2023

• Can Language Model Moderators Improve the Health of Online Discourse? papers
• Safer-Instruct: Aligning Language Models with Automated Preference Data papers
• CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation papers
• Positive Reframing Keyboard projects
• Neural Story Planning papers
• Investigating AAVE in Question Answering Systems papers