Huan Wang

Orcid: 0009-0005-1505-0769

Affiliations:
  • Salesforce Research, AI Research, Palo Alto, CA, USA


According to our database1, Huan Wang authored at least 101 papers between 2018 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Whisper-AuT: Domain-Adapted Audio Encoder for Efficient Audio-LLM Training.
CoRR, April, 2026

Enterprise Sales Copilot: Enabling Real-Time AI Support with Automatic Information Retrieval in Live Sales Calls.
CoRR, March, 2026

Building Enterprise Realtime Voice Agents from Scratch: A Technical Tutorial.
CoRR, March, 2026

Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language Models.
CoRR, March, 2026

VoiceAgentRAG: Solving the RAG Latency Bottleneck in Real-Time Voice Agents Using Dual-Agent Architectures.
CoRR, March, 2026

AudioCapBench: Quick Evaluation on Audio Captioning across Sound, Music, and Speech.
CoRR, February, 2026

Prompt Optimization Via Diffusion Language Models.
CoRR, February, 2026

2025
LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering.
CoRR, November, 2025

GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs.
CoRR, November, 2025

Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics.
CoRR, October, 2025

xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning.
CoRR, October, 2025

ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning.
CoRR, October, 2025

Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels.
CoRR, October, 2025

CoDA: Coding LM via Diffusion Adaptation.
CoRR, October, 2025

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning.
CoRR, September, 2025

LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering.
CoRR, September, 2025

UserBench: An Interactive Gym Environment for User-Centric Agents.
CoRR, July, 2025

Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models.
CoRR, July, 2025

LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback.
CoRR, June, 2025

Entropy-Based Block Pruning for Efficient Large Language Models.
CoRR, April, 2025

APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay.
CoRR, April, 2025

PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data.
CoRR, February, 2025

xLAM: A Family of Large Action Models to Empower AI Agent Systems.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025


ActionStudio: A Lightweight Framework for Data and Training of Large Action Models.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

LATTE: Learning to Think with Vision Specialists.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

SlackAgents: Scalable Collaboration of AI Agents in Workspaces.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

Text2Data: Low-Resource Data Generation with Textual Control.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024
TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-Action.
CoRR, 2024

SpecTool: A Benchmark for Characterizing Errors in Tool-Use LLMs.
CoRR, 2024

Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding.
CoRR, 2024

PRACT: Optimizing Principled Reasoning and Acting of LLM Agent.
CoRR, 2024

xLAM: A Family of Large Action Models to Empower AI Agent Systems.
CoRR, 2024

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models.
CoRR, 2024

Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents.
CoRR, 2024

Enabling High Data Throughput Reinforcement Learning on GPUs: A Domain Agnostic Framework for Data-Driven Scientific Research.
CoRR, 2024

APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets.
CoRR, 2024

MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases.
CoRR, 2024

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System.
CoRR, 2024

AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning.
CoRR, 2024

Editing Arbitrary Propositions in LLMs without Subject Labels.
CoRR, 2024

Towards More Robust and Accurate Sequential Recommendation with Cascade-guided Adversarial Training.
Proceedings of the 2024 SIAM International Conference on Data Mining, 2024

On the Unlikelihood of D-Separation.
Proceedings of the International Conference on Probabilistic Graphical Models, 2024

APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

xGen-VideoSyn-1: High-Fidelity Text-to-Video Synthesis with Compressed Representations.
Proceedings of the Computer Vision - ECCV 2024 Workshops, 2024

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI.
Proceedings of the Findings of the Association for Computational Linguistics: EACL 2024, 2024

HIVE: Harnessing Human Feedback for Instructional Visual Editing.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Causal Layering via Conditional Entropy.
Proceedings of the Causal Learning and Reasoning, 2024

Personalized Multi-task Training for Recommender System.
Proceedings of the IEEE International Conference on Big Data, 2024

2023
Merlion: End-to-End Machine Learning for Time Series.
J. Mach. Learn. Res., 2023

BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents.
CoRR, 2023

Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization.
CoRR, 2023

REX: Rapid Exploration and eXploitation for AI Agents.
CoRR, 2023

On the Unlikelihood of D-Separation.
CoRR, 2023

Salesforce CausalAI Library: A Fast and Scalable Framework for Causal Analysis of Time Series and Tabular Data.
CoRR, 2023

Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System.
Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue, 2023

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Lower Bounds for Learning in Revealing POMDPs.
Proceedings of the International Conference on Machine Learning, 2023

Improved Online Conformal Prediction via Strongly Adaptive Online Learning.
Proceedings of the International Conference on Machine Learning, 2023

CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Zero-shot Item-based Recommendation via Multi-task Product Knowledge Graph Pre-Training.
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023

2022
WarpDrive: Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU.
J. Mach. Learn. Res., 2022

Generating Negative Samples for Sequential Recommendation.
CoRR, 2022

A Conversational Paradigm for Program Synthesis.
CoRR, 2022

Converse: A Tree-Based Modular Task-Oriented Dialogue System.
CoRR, 2022

Local calibration: metrics and recalibration.
Proceedings of the Uncertainty in Artificial Intelligence, 2022

Policy Optimization for Markov Games: Unified Framework and Faster Convergence.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Efficient and Differentiable Conformal Prediction with General Function Classes.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE.
CoRR, 2021

Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles.
CoRR, 2021

Merlion: A Machine Learning Library for Time Series.
CoRR, 2021

Localized Calibration: Metrics and Recalibration.
CoRR, 2021

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Evaluating State-of-the-Art Classification Models Against Bayes Optimality.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Understanding the Under-Coverage Bias in Uncertainty Estimation.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization.
Proceedings of the 38th International Conference on Machine Learning, 2021

Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification.
Proceedings of the 38th International Conference on Machine Learning, 2021

How Important is the Train-Validation Split in Meta-Learning?
Proceedings of the 38th International Conference on Machine Learning, 2021

Unsupervised Paraphrasing with Pretrained Language Models.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch.
Proceedings of the Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, 2021

2020
Unsupervised Paraphrase Generation via Dynamic Blocking.
CoRR, 2020

Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning.
CoRR, 2020

Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width.
CoRR, 2020

Towards Understanding Hierarchical Learning: Benefits of Neural Representations.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Assessing Local Generalization Capability in Deep Models.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019
Attentive Student Meets Multi-Task Teacher: Improved Knowledge Distillation for Pretrained Models.
CoRR, 2019

Global Capacity Measures for Deep ReLU Networks via Path Sampling.
CoRR, 2019

On the Generalization Gap in Reparameterizable Reinforcement Learning.
Proceedings of the 36th International Conference on Machine Learning, 2019

2018
Identifying Generalization Properties in Neural Networks.
CoRR, 2018


  Loading...