Wenbo Ding

Action-conditioned verification can boost success rates in mobile manipulation tasks by over 8% while enhancing timely recall by nearly 30%.

FutureNav redefines VLN by simultaneously predicting actions and modeling world states, achieving unprecedented performance with a streamlined architecture.

Shifting the focus from marginal probabilities to joint trajectory probabilities, dVLA-RL achieves unprecedented success rates in robotic manipulation tasks.

A unified modeling framework for TENGs reveals the intricate interplay of charge states, transforming how we simulate and design energy-harvesting devices.

Achieving over 555 FPS in tactile simulations, TaCauchy delivers unprecedented accuracy in mechanical stress computation for robotics applications.

Infini Memory redefines long-term memory for LLMs, achieving a 64.7% score on MemoryAgentBench by structuring memory as topic documents that evolve over time.

OneVLA unifies navigation and manipulation tasks into a single framework, enabling robots to seamlessly interpret commands and interact with their environments like never before.

Robots can now navigate complex outdoor environments using only high-level human instructions and readily available GPS/map data, bypassing the need for expensive HD maps or limited short-horizon policies.

Robots can now leverage human intuition for manipulation tasks, learning from a massive video dataset to improve motion plausibility and robustness, even when conditions change.

Visual RL agents can recover near-perfect performance even under severe, dynamically changing visual corruptions by learning to disentangle task-relevant foreground from perturbation artifacts.