5 papers
DIVA: Dual-Space Intent-Aware Visual Attenuation for Vision-Language-Action Policies
Kaixi Feng, Guoheng Sun, Ziyao Wang +3
Vision-language-action (VLA) policies typically feed dense visual patch tokens into a language-action backbone, preserving scene context but offering no explicit mechanism to regul…
PAIR: Bridging Perception and Action in Vision-Language-Action Models
Kaixi Feng, Guoheng Sun, Ang Li +1
Vision-language-action (VLA) models map visual observations and language instructions to continuous robot actions. This task requires a transition from representations that describ…
Causeway: Restoring Task Accessibility for Instruction Switching in VLA Policies
Qingzi Wang, Kaixi Feng, Guangyao Shi +3
Vision-language-action (VLA) policies can execute many tasks from standard initial states, yet a new instruction may fail after another task has altered the robot's physical state.…
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?
Guoheng Sun, Kaixi Feng, Shwai He +8
Vision-Language-Action (VLA) models enable instruction-driven robotic manipulation, but they inherit oversized language backbones from pretrained VLMs whose capacity far exceeds wh…
ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models
Guoheng Sun, Tingting Du, Kaixi Feng +6
Vision-Language-Action (VLA) models enable instruction-following robotic manipulation, but they are typically pretrained on 2D data and lack 3D spatial understanding. An effective…