Changsheng Zhao

Affiliations:
  • Meta, CA, USA
  • Samsung Research America, USA (former)
  • Peking University, Beijing, China (former)
  • Columbia University, New York, NY, USA (former)


According to our database1, Changsheng Zhao authored at least 30 papers between 2019 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
WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points.
CoRR, May, 2026

Exploring Audio Hallucination in Egocentric Video Understanding.
CoRR, April, 2026

RPRA: Predicting an LLM-Judge for Efficient but Performant Inference.
CoRR, April, 2026

Neural Computers.
CoRR, April, 2026

dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models.
CoRR, March, 2026

EgoAVU: Egocentric Audio-Visual Understanding.
CoRR, February, 2026

STEM: Scaling Transformers with Embedding Modules.
CoRR, January, 2026

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice.
CoRR, January, 2026

2025
DepthLM: Metric Depth From Vision Language Models.
CoRR, September, 2025

MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes.
CoRR, September, 2025

ParetoQ: Scaling Laws in Extremely Low-bit LLM Quantization.
CoRR, February, 2025

Streamlining Language Models via Semantic Basis Analysis.
Trans. Mach. Learn. Res., 2025

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

Agent-as-a-Judge: Evaluate Agents with Agents.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

SpinQuant: LLM Quantization with Learned Rotations.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations.
CoRR, 2024

Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications.
CoRR, 2024

Not All Weights Are Created Equal: Enhancing Energy Efficiency in On-Device Streaming Speech Recognition.
CoRR, 2024

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

On the Open Prompt Challenge in Conditional Audio Generation.
Proceedings of the IEEE International Conference on Acoustics, 2024

Scaling Parameter-Constrained Language Models with Quality Data.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: EMNLP 2024, 2024

Target-Aware Language Modeling via Granular Data Sampling.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

LLM-QAT: Data-Free Quantization Aware Training for Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023
Towards Zero-Shot Multilingual Transfer for Code-Switched Responses.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

Revisiting Sample Size Determination in Natural Language Understanding.
Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2021
Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding.
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021

Automatic Mixed-Precision Quantization Search of BERT.
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

2019
Interactive Topic Model with Enhanced Interpretability.
Proceedings of the Joint Proceedings of the ACM IUI 2019 Workshops co-located with the 24th ACM Conference on Intelligent User Interfaces (ACM IUI 2019), 2019


  Loading...