Guoheng Sun

Orcid: 0009-0004-4346-8516

According to our database1, Guoheng Sun authored at least 31 papers between 2023 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines.
CoRR, April, 2026

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers.
CoRR, April, 2026

TOPCELL: Topology Optimization of Standard Cell via LLMs.
CoRR, April, 2026

Cognibit: From Digital Exhaustion to Real-World Connection Through Gamified Territory Control and LLM-Powered Twin Networking.
CoRR, April, 2026

Demystifying When Pruning Works via Representation Hierarchies.
CoRR, March, 2026

ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models.
CoRR, February, 2026

FedMOA: Federated GRPO for Personalized Reasoning LLMs under Heterogeneous Rewards.
CoRR, February, 2026

Towards Building Non-Fine-Tunable Foundation Models.
CoRR, February, 2026

Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines.
Trans. Mach. Learn. Res., 2026

Uncovering the Redundancy in Transformers via a Unified Study of Layer Dropping.
Trans. Mach. Learn. Res., 2026

Enhancing the Security of Large Character Set CAPTCHAs Using Transferable Adversarial Examples.
IEEE Trans. Dependable Secur. Comput., 2026

VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation.
Proceedings of the Great Lakes Symposium on VLSI 2026, 2026

2025
Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation.
CoRR, August, 2025

CogniPair: From LLM Chatbots to Conscious AI Agents - GNWT-Based Multi-Agent Digital Twins for Social Pairing - Dating & Hiring Applications.
CoRR, June, 2025

Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL.
CoRR, May, 2025

Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services.
CoRR, May, 2025

CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs.
CoRR, May, 2025

NetSight: Graph Attention Based Traffic Forecasting in Computer Networks.
CoRR, May, 2025

SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning.
CoRR, April, 2025

Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices.
CoRR, March, 2025

EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices.
Proceedings of the 23rd Annual International Conference on Mobile Systems, 2025

Towards counterfactual fairness through auxiliary variables.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Router-Tuning: A Simple and Effective Approach for Dynamic Depth.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024
Towards counterfactual fairness thorough auxiliary variables.
CoRR, 2024

Fair Diagnosis: Leveraging Causal Modeling to Mitigate Medical Bias.
CoRR, 2024

Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers.
CoRR, 2024

What Matters in Transformers? Not All Attention is Needed.
CoRR, 2024

Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023
Fighting Attacks on Large Character Set CAPTCHAs Using Transferable Adversarial Examples.
Proceedings of the International Joint Conference on Neural Networks, 2023


  Loading...