arXiv AI September 10, 2026 By Aman Mehta, Riya Baviskar

CALIPER: Clean Scenes Cannot Rank Physical Inference in Pretrained Visual Representations

CALIPER is a new benchmark that tests whether pretrained visual encoders can infer physical properties such as mass and friction from images. The test involves striking an object twice at known speeds, showing a third strike only up to contact, and asking a linear readout on frozen features to predict how far the object slides. Results show that in clean, fixed‑camera scenes all representations perform similarly, but when camera, lighting, and clutter are varied, only encoders that truly infer physics—like V‑JEPA 2—maintain performance, while random or raw pixel representations fail.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computer Vision

Sep 10

MotionBlind: Probing the Illusion of Motion Understanding in Video-LLMs

arXiv:2609.09528v1 Announce Type: new Abstract: Video large language models (Video-LLMs) are increasingly used as the perceptual front end of world models, a role that assumes they can read motion: h...

By Dhairya Bhatia, Bishoy Galoaa, Oliver Fritsche, Shahid Kamal, Muhammad Obaidullah Abdul Salam, Umer Saleem, Om Rastogi, Frania Felix Chettiar, Nesli Erdogmus, Sarah Ostadabbas

llms benchmarks

arXiv Computer Vision

4d ago

Learning Manipulation-Sufficient Representations via Outcome Bottlenecks

arXiv:2609.13235v1 Announce Type: cross Abstract: Networked manipulation endpoints couple perception to actuation across compute- and bandwidth-limited links, yet commonly exchange dense geometric st...

By Md Selim Sarowar, Sungho Kim

robotics

arXiv Machine Learning

Aug 18

RigidBench: Evaluating Rigid-Body Physics in Video Generation Models

arXiv:2608. 15555v1 Announce Type: cross Abstract: Video models are increasingly used to predict what happens next in a scene, yet the metrics commonly used to compare their outputs say little about whether the predicted objects move correctly.

By Swarnim Jain, Shangzhe Wu

llms diffusion fine-tuning benchmarks

arXiv Machine Learning

4d ago

GroundBench: A Factorized, Counterfactual Benchmark for Locating VLM Affordance Failures

arXiv:2609.13308v1 Announce Type: cross Abstract: A companion evaluation found that naming the target part in a manipulation prompt increased action accuracy by 0.32-0.63 across eight vision-language...

By Sarthak Sattigeri

llms robotics multimodal benchmarks

arXiv AI

Jul 16

Accuracy Without Grounding: Diagnosing Visual Dependency Dissociation in Video LLM Benchmarks

arXiv:2607. 13305v1 Announce Type: cross Abstract: Benchmark accuracy in video large language models (LLMs) is often treated as evidence of visual understanding.

By Jae Joong Lee

llms benchmarks

Hugging Face Trending Papers

Jul 15

Kepler-Encoder-v0.1: Towards a Multimodal Embedding Model for Robots

A robot must understand the state of its own body, but a camera sees only part of it. Force and contact leave almost no trace in a single frame, and raw vision features read force at $R^2$ at or below $0.

rag diffusion robotics multimodal