Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
Two papers accepted at ICML 2026
Published:
Two papers (HyperMLP and StretchTime) are accepted to ICML 2026:
Free Energy Mixer accepted to ICLR 2026
Published:
Free Energy Mixer has been accepted to ICLR 2026.
Links: OpenReview page · Code · Poster
ZeroS accepted to NeurIPS 2025 (Spotlight)
Published:
ZeroS: Zero‑Sum Linear Attention for Efficient Transformers has been accepted to NeurIPS 2025 (Spotlight).
Links: NeurIPS page · OpenReview PDF · Poster
Two papers accepted at ICML 2025
Published:
Two papers (WAVE and SAMoVAR) are accepted to ICML 2025 (Poster):
ICTSP accepted to ICLR 2025
Published:
In‑context Time Series Predictor is accepted to ICLR 2025 (Poster).
Links: OpenReview page · arXiv · Slides · Poster
CATS accepted at ICML 2024
Published:
CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables is accepted to ICML 2024 (Poster).
Links: PMLR page · PDF · arXiv · Code · Poster
ARM accepted at ICLR 2024
Published:
ARM: Refining Multivariate Forecasting with Adaptive Temporal‑Contextual Learning is accepted to ICLR 2024 (Poster).
Links: ICLR proceedings page · OpenReview PDF · arXiv · Poster
awards
M.H. Stewart Fellowship
Published:
Fellowship awarded by Georgia Tech.
Margaret and Stephen Kendrick PhD Student Fellowship for Research Excellence
Published:
Fellowship for research excellence awarded by Georgia Tech.
Best Poster Award (1st Place), AASF AIX Summit 2026
Published:
Best Poster Award (1st Place) at AASF AIX Summit 2026 for the Free Energy Mixer poster.
portfolio
publications
ARM: Refining Multivariate Forecasting with Adaptive Temporal‑Contextual Learning
Published in ICLR 2024 (Poster), 2024
Presents ARM with AUEL, Random Dropping, and multi‑kernel local smoothing to better capture series‑wise patterns and inter‑series dependencies for long‑term multivariate TSF.
CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables
Published in ICML 2024 (Poster), PMLR 235: 32990–33006, 2024
Constructs Auxiliary Time Series (ATS) as exogenous inputs to capture inter‑series relations; identifies continuity, sparsity, and variability principles; improves multivariate TSF even with simple predictors.
In‑context Time Series Predictor
Published in ICLR 2025 (Poster), 2025
Reformulates TSF as in‑context learning by constructing tokens of (lookback, future) task pairs, enabling Transformers to adapt predictors from context without parameter updates.
WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting
Published in ICML 2025 (Poster), PMLR 267: 40464–40490, 2025
Adds ARMA structure to autoregressive attention via a weighted varying gate, decoupling long‑range and local effects and improving TSF quality without increasing asymptotic complexity.
Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting
Published in ICML 2025 (Poster), PMLR 267: 40848–40867, 2025
Shows that a linear attention layer can be interpreted as a dynamic VAR; proposes SAMoVAR to realign multi‑layer Transformers with autoregressive forecasting for improved interpretability and accuracy.
ZeroS: Zero‑Sum Linear Attention for Efficient Transformers
Published in NeurIPS 2025 (Spotlight), 2025
Introduces Zero‑Sum Linear Attention (ZeroS), which removes the uniform zero‑order term and reweights residuals to enable stable positive/negative attention weights, allowing contrastive operations within a single layer while retaining O(N) complexity.
Free Energy Mixer
Published in ICLR 2026, 2026
Introduces Free Energy Mixer (FEM), which interprets (q,k) attention scores as a prior and performs a log-sum-exp free-energy readout to reweight values at the channel level, enabling a smooth transition from mean aggregation to selective channel-wise retrieval without increasing asymptotic complexity.
StretchTime: Adaptive Time Series Forecasting via Symplectic Attention
Published in ICML 2026, 2026
Introduces adaptive time series forecasting via symplectic attention, developed through mentored undergraduate research with Jiecheng Lu as corresponding author.
HyperMLP: An Integrated Perspective for Sequence Modeling
Published in ICML 2026, 2026
Presents an integrated dynamic-MLP perspective on sequence modeling, reinterpreting attention heads through context-instantiated MLP computation and learnable sequence-space mixing.
talks
Rethinking Sequence Modeling: LLM Scaling Laws, Expressivity-Efficiency Tradeoffs, and the Role of Architecture
Published:
PhD seminar talk at Georgia Tech ISyE on scaling laws, expressivity-efficiency tradeoffs, and the role of architecture in sequence modeling.
Rethinking Sequence Modeling with HyperMLP: An Integrated Architectural Perspective
Published:
Invited online talk hosted by Tsinghua University on HyperMLP and an integrated view of sequence modeling.
Rethinking Sequence Modeling: LLM Scaling Laws, Expressivity-Efficiency Tradeoffs, and the Role of Architecture
Published:
ML PhD seminar talk at Georgia Tech on scaling laws, expressivity-efficiency tradeoffs, and the role of architecture in sequence modeling.
teaching
ISyE 4031 Regression and Forecasting
Independent Instructor, Georgia Institute of Technology, 2026
Independent instructor for ISyE 4031 Regression and Forecasting at Georgia Tech in Summer 2026.