activity
20242026
collaborators

13 papers

cs.LG2026

Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns

Dong Tian, Onur Celik, Gerhard Neumann

We introduce a sequence-conditioned critic for Soft Actor-Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated -step targets. Unli…

cs.AI2026

Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies

Zirui Tang, Xuanhe Zhou, Yumou Liu +19

Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling t…

cs.CV2026

NAMI: Efficient Image Generation via Bridged Progressive Rectified Flow Transformers

Yuhang Ma, Bo Cheng, Shanyuan Liu +4

Flow-based Transformer models have achieved state-of-the-art image generation performance, but often suffer from high inference latency and computational cost due to their large pa…

cs.RO2026

PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning

Xiaogang Jia, Qian Wang, Anrui Wang +12

Robotic manipulation systems benefit from complementary sensing modalities, where each provides unique environmental information. Point clouds capture detailed geometric structure,…

cs.RO2025

BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning

Hongyi Zhou, Weiran Liao, Xi Huang +11

We present the B-spline Encoded Action Sequence Tokenizer (BEAST), a novel action tokenizer that encodes action sequences into compact discrete or continuous tokens using B-splines…

cs.RO2025

IRIS: An Immersive Robot Interaction System

Xinkai Jiang, Qihao Yuan, Enes Ulas Dincer +11

This paper introduces IRIS, an Immersive Robot Interaction System leveraging Extended Reality (XR). Existing XR-based systems enable efficient data collection but are often challen…