Yusuke Iwasawa

Robots can now intelligently choose camera angles to answer questions by predicting the utility of unseen views, bypassing costly real-time rendering.

Frozen 4B image generators can outperform proprietary models at multi-subject composition simply by letting an autonomous coding agent iteratively rewrite their Python orchestration harnesses.

This work evaluates cross-embodiment transfer on RoboTwin 2.0 in a controlled setup, two bimanual robots demonstrate disjoint task sets, a policy is trained on all the demonstrations, and each robot is evaluated closed-loop on the tasks only the other demonstrated.

A compact 0.54M-parameter policy can achieve near-optimal performance on the LIBERO benchmark, challenging the notion that larger models are always better. WHY_IT MATTERS: This research could redefine our understanding of model efficiency in VLA systems, paving the way for more deployment-efficient robotic policies.

Performance gaps in multilingual medical evaluations reveal that proprietary models outperform open-source ones, but translation quality can swing results dramatically.

SCSE transforms recurrent computation in Looped Transformers by ensuring that deviations from a learned anchor enhance performance without compromising stability.

Temporally centered SIGReg boosts multi-task learning performance by 1.7x, revealing critical incompatibilities in latent representation structures.

NavWAM turns visual foresight into executable robot actions, outperforming traditional planning methods in real-world navigation scenarios.

Ditch the energy functions: C-voting unlocks better test-time reasoning in recurrent models by simply picking the most confident trajectory.

Forget Transformers; this new recurrent architecture learns more stable representations and generalizes better out-of-distribution by interleaving fast latent updates with slower, self-organizing observation processing.

Current multimodal LLMs struggle to count objects and ground evidence in videos longer than 30 minutes, achieving only ~25% accuracy compared to human performance on a new benchmark.

LLMs' chain-of-thought reasoning often falls apart due to factual incompleteness, with errors compounding across multiple hops, as revealed by a new multi-hop QA dataset.

Predict transformer training failures *before* you even start training, with 99.5% accuracy, using just a single forward pass.

LLMs that ace medical exams still fumble basic clinical judgment, prematurely deciding cases or abstaining unnecessarily when information is incomplete, revealing a critical gap in their real-world applicability.