Clearing up a robot’s fuzzy memory
A new system identifies and corrects unreliable object descriptions stored in a robot’s memory, improving the robot’s ability to interact with its environment.
More from the blog
ToyBlocks: A controlled world for robot learning and evaluation
FramioCam: Capture Screenshots and Edit Videos in Chrome
FramioCam combines screenshots, screen recording, annotations, and video editing in Chrome. Discover how it simplifies content creation and what you get for free.
ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model
A Blog post by IBM Research on Hugging Face
Giving AI a “crystal clear” view of the materials world
New research can help AI models understand crystalline materials in 3D and reason about their properties.
Related papers
Gibson Env: Real-World Perception for Embodied Agents
This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.
RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design
RMBench is introduced, a simulation benchmark comprising 9 manipulation tasks that span multiple levels of memory complexity, enabling systematic evaluation of policy memory capabilities and Mem-0, a modular manipulation policy with explicit memory components designed to support controlled ablation studies.
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
This work characterize models from this family of methods as JEPA-WMs and investigates the technical choices that make algorithms from this class work, and proposes a model that outperforms two established baselines, DINO-WM and V-JEPA-2-AC, in both navigation and manipulation tasks.
StarVLA-α: Reducing Complexity in Vision-Language-Action Systems
This work introduces StarVLA-$\alpha, a simple yet strong baseline designed to study VLA design choices under controlled conditions that deliberately minimizes architectural and pipeline complexity to reduce experimental confounders and enable systematic analysis.