AI Research
Featured Research
Selected advancements in AI agents, personalization, and LLMs.
All Publications
Paper titles link to the full publication. Author lists are omitted for readability.
Publications and patents are on my Google Scholar.
LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
arXiv • 2025
Grounded Test-Time Adaptation for LLM Agents
arXiv • 2025
CoDA: Coding LM via Diffusion Adaptation
Submitted • 2025
APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
NeurIPs Datasets & Benchmarks • 2025
Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models
Technical Report • 2025
xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
Submitted • 2025
Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
Submitted • 2025
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models
EMNLP Demo • 2025
Entropy-Based Block Pruning for Efficient Large Language Models
Submitted • 2025
LATTE: Learning to Think with Vision Specialists
EMNLP • 2025
ToolScan: A Benchmark for Characterizing Errors in Tool-Use LLMs
ICLR Workshop • 2025
Personalized Multi-task Training for Recommender System
IEEE Big Data • 2025
APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets
NeurIPs Datasets & Benchmarks • 2024
MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases
Technical Report • 2024
AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System
Databricks LLM Systems Workshop • 2024
AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning
Technical Report • 2024
Causal Layering via Conditional Entropy
CLeaR • 2024
Editing Arbitrary Propositions in LLMs without Subject Labels
Submitted • 2024
DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation
Submitted • 2024
SIGDIAL • 2023
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI
EACL • 2024
Towards More Robust and Accurate Sequential Recommendation with Cascade-guided Adversarial Training
SDM • 2024
On the Unlikelihood of D-Separation
PMLR • 2024
Technical Report • 2023
Dynamic Causal Collaborative Filtering
CIKM • 2023
Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution
NeurIPs Workshop • 2022
Deconfounded Causal Collaborative Filtering
Transactions on Recommender Systems • 2022
Communication-Aware Collaborative Learning
AAAI • 2020
On the Resilience of Bipartite Networks
Allerton • 2018