Selected work

Projects

Research, modeling, and machine-learning work spanning embodied AI, computer vision, language models, optimization, and predictive systems. Select any project to read the complete motivation, method, results, and contribution.

May 2025 – Oct 2025 LISN social navigation system

ICRA 2026 · Accepted

LISN: Language-Instructed Social Navigation

  • Introduced a benchmark for instruction-following social navigation.
  • Combined VLM reasoning with real-time costmap and controller modulation.
  • Achieved 91.3% average success across challenging human–robot scenarios.

Project details → · Paper · Video

Nov 2024 – Mar 2025 Asynchronous structure and motion solver

ICCV 2025 · Highlight

A Linear N-Point Solver for Asynchronous Tracks

  • Unified structure and linear-motion estimation across arbitrary timestamps and views.
  • Supported global-shutter, rolling-shutter, event-camera, and mixed sensor tracks.
  • Delivered 63 μs CPU runtime with 10–30% lower velocity error.

Project details → · Paper · Code

Mar 2025 – May 2025 LLM concept-subspace analysis

UC Berkeley · EECS 182

Beyond the LRH: Concept Subspaces in LLMs

  • Identified limits of single-direction representations for complex semantics.
  • Designed a multidimensional concept-subspace steering method.
  • Improved concept alignment from 0.5/5 to 5.0/5 using five latent directions.

Project details →

Feb 2025 – May 2025 Sustainable tourism modeling

MCM 2025 · Outstanding Winner & AMS Award

Rebalancing Nature’s Scale

  • Built a coupled ODE model for tourism, environmental pressure, and local revenue.
  • Optimized interventions and tax allocation through simulation and AHP.
  • Placed Top 3 among 21,054 teams in the Mathematical Contest in Modeling.

Project details →

Feb 2025 Equity derivative hedging pipeline

Bay Area Data Science Summit · First Place

MLP for Optimal Equity Derivative Hedging

  • Led an international team in a UC Berkeley competition endorsed by Wells Fargo.
  • Built an MLP-based, exposure-aware equity derivative hedging pipeline.
  • Reduced test-set premium cost by 64.5% while maintaining a $10M exposure target.

Project details → · Slides · Paper · Code

Feb 2024 – Jun 2024 Wine quality prediction project

Machine Learning Project

Hybrid ML for Quality Prediction

  • Used PCA to compress correlated physicochemical features and isolate stable signal.
  • Applied Huber loss to reduce sensitivity to noisy labels and heavy-tailed residuals.
  • Combined robust preprocessing with classical and ensemble predictive models.

Project details → · Slides · Paper · Code