← Search

Zhen Tian

9 accepted papers

2026

HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning

ICML 2026poster

Domain Incremental Learning is a critical scenario that requires models to continuously adapt to new data domains without retraining. However, domain shifts often cause severe performance degradation. To address this, we propose Hybrid Energy-Distance Prompt, a domain-incremental framework inspired …

Cited by 0SourceScholar
2026

Information Geometry Loss for Time Series Forecasting

ICML 2026poster

Time series forecasting fundamentally involves learning probability distributions over future observations. However, existing loss functions rely on point-wise Euclidean metrics, neglecting the intrinsic geometric structure of probability distributions. This leads to suboptimal alignment between pre…

Cited by 0SourceScholar
2026

PECHC: Robust Tactile Grasping Stabilization in Vision-Denied Peripersonal Space

IJCAI 2026

In the final “Last-Centimeter” phase of manipulation, visual occlusion and calibration errors often make vision unreliable, causing robots to suffer high failure rates due to local pose uncertainty and deviations between simulated and real-world dynamics. To address these challenges, this paper prop

Cited by 0Scholar
2025

EchoDiffusion: Waveform Conditioned Diffusion Models for Echo-Based Depth Estimation

AAAI 2025technical

To extract spatial information, depth estimation using conventional echo-based methods typically employs models with encoder-decoder architectures, such as UNet. However, these methods may face challenges in extracting fine details from echo waveforms and handling multi-scale feature extraction with…

2025

Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation

ICCV 2025poster

Federated Unlearning (FU) should satisfy three key requirements: a guarantee of data erasure, preservation of model utility, and reduction of unlearning time. Recent studies focus on identifying and modifying original model parameters relevant to unlearning data. While they can achieve faster unlear…

2025

MobiExo: GPS-SLAM Fusion for Seamless Indoor-Outdoor Mobile Manipulation with Hand-Foot Coordination

IROS 2025

Teleoperation systems for mobile robots face significant challenges in achieving seamless coordination across dynamic environments. We present MobiExo, a teleoperation system that unlocks seamless indoor-outdoor mobile manipulation. Our approach tackles two fundamental challenges: robust cross-envir

Cited by 0SourcecodeScholar
2024

Exploring Context Window of Large Language Models via Decomposed Positional Vectors

NeurIPS 2024spotlight

Transformer-based large language models (LLMs) typically have a limited context window, resulting in significant performance degradation when processing text beyond the length of the context window. Extensive studies have been proposed to extend the context window and achieve length extrapolation of…

Cited by 9SourcePDFScholar