Shengji Tang

Orcid: 0009-0001-3456-8310

According to our database1, Shengji Tang authored at least 17 papers between 2022 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction.
CoRR, May, 2026

Small Model as Master Orchestrator: Learning Unified Agent-Tool Orchestration with Parallel Subtask Decomposition.
CoRR, April, 2026

LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing.
CoRR, January, 2026

Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale.
CoRR, January, 2026

A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
Stimulative Training++: Go Beyond the Performance Limits of Residual Networks.
IEEE Trans. Pattern Anal. Mach. Intell., August, 2025

Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback.
CoRR, August, 2025

CTTS: Collective Test-Time Scaling.
CoRR, August, 2025

Open-Source LLMs Collaboration Beats Closed-Source LLMs: A Scalable Multi-Agent System.
CoRR, July, 2025

WI3D: Weakly Incremental 3D Detection via Vision Foundation Models.
IEEE Trans. Multim., 2025

DreamFrame: Enhancing Video Understanding via Automatically Generated QA and Style-Consistent Keyframes.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Multi-dimensional Search with Strip Convolution and R-Squared Loss for Lane Detection.
Proceedings of the International Joint Conference on Neural Networks, 2024

Enhanced Sparsification via Stimulative Training.
Proceedings of the Computer Vision - ECCV 2024, 2024

Boosting Residual Networks with Group Knowledge.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2022
Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022


  Loading...