activity
20242026
collaborators

8 papers

cs.RO2026

ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies

Bingjia Huang, Xiangyu Li, Xiang Wang +7

Generative robot policies fail unpredictably at deployment: they hesitate at critical moments, drift off-task, or commit to unrecoverable actions. Existing online failure detectors…

cs.DC2026

Unfolding an Atomistic World: Atomistic Simulation of Reactor Pressure Vessel Steel Across Year-and-Meter Scales

Haozhi Han, Ruge Zhang, Haoquan Chen +8

Lifetime prediction of reactor pressure vessel (RPV) steel requires bridging atomistic degradation mechanisms with service-scale spatial and temporal regimes, from Angstroms and pi…

cs.LG2025

Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity

Tuowei Wang, Kun Li, Zixu Hao +5

The adaptation of pre-trained large language models (LLMs) to diverse downstream tasks via fine-tuning is critical for numerous applications. However, the inefficiency of parameter…

cs.LG2025

Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking

Tuowei Wang, Ruwen Fan, Minxing Huang +6

Large Language Models (LLMs) have achieved remarkable success across various domains, yet deploying them on mobile devices remains an arduous challenge due to their extensive compu…

cs.AI2025

SwarmThinkers: Learning Physically Consistent Atomic KMC Transitions at Scale

Qi Li, Kun Li, Haozhi Han +6

Can a scientific simulation system be physically consistent, interpretable by design, and scalable across regimes--all at once? Despite decades of progress, this trifecta remains e…

cs.CE2025

SparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation

Qi Li, Kun Li, Haozhi Han +7

Sparse Tensor Cores offer exceptional performance gains for AI workloads by exploiting structured 2:4 sparsity. However, their potential remains untapped for core scientific worklo…