MLINFO COLLECTION
Vision-Language-Action (VLA) policies demonstrate remarkable semantic generalization, yet remain highly vulnerable to out-of-distribution (OOD) visual shifts during execution. While existing…
Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for enhancing the video reasoning capability of Large Multimodal Models (LMMs). Despite its…
Humanoids and other legged robots operating in complex environments must remember information that leaves their field of view and only becomes relevant much later. Reinforcement learning policies…
Legged robots for lunar exploration must be designed for low gravity, where reduced contact forces and long flight phases make leg morphology and controller choice interdependent. We study this for a…
Accurate forecasting of global total electron content (TEC) is important for space weather monitoring and the reliable operation of satellite communication and navigation systems. We propose a…
Knowledge distillation compresses large language models into compact students that preserve aggregate metrics, yet the mechanistic consequences of depth-reduction distillation remain largely…
Reliable real-time 3D object detection based on LiDAR and camera data is critical for safety in autonomous driving, where systems must accurately perceive their surroundings with minimal latency.…
Pruned language models are judged almost entirely by accuracy and perplexity, which assumes that preserved output behaviour implies preserved internal computation. We test this assumption with a…
We introduce SERF (Self-Regularized Flow Language Models), a simple self-supervised framework for improving continuous diffusion language models by exploiting the denoising trajectory itself. While…
Active simultaneous localization and mapping (SLAM) addresses the problem of planning robot motion to build complete and accurate maps of unknown environments through efficient exploration while…
World-action models (WAMs) incorporate the prediction of future observations into robot policy learning. However, most WAMs build on billion-parameter vision-language or video-generation backbones,…
Parameter-efficient fine-tuning (PEFT) methods adapt large models by introducing a small number of trainable parameters. However, we find that these parameters still contain redundancy and can be…
Sparse mixture-of-experts (MoE) language-model training can exhibit large loss spikes with Muon-family optimizers. We introduce EnergyCal, a lightweight rule that attenuates routed-expert updates…
Reinforcement learning with verifiable rewards (RLVR) has shown strong empirical gains in improving the reasoning ability of large language models (LLMs) on tasks such as mathematics and programming.…
Field applications in chemical sensing, from portable safety monitors to mobile robots, require models that are lightweight, fast to respond, and can be recalibrated from limited labelled data.…
We study how boundary geometry affects $L^q$ approximation by shallow ReLU neural networks on convex bodies $K\subset\mathbb R^d$. The target classes are unit balls of weighted variation spaces that…
World Action Models (WAMs) learn representations for robot control by coupling future visual prediction with action generation. Successful manipulation depends primarily on how the robot and…
Generative planners are often evaluated by the trajectories they can generate, although closed-loop driving ultimately depends on the single candidate committed to control. We identify this mismatch…
Humanoid parkour requires robots to reason about future footholds and whole-body motions over highly discontinuous terrain. We revisit the information asymmetry in asymmetric actor-critic learning…
Pretrained video generation models encode rich priors about physical interactions, but leveraging them for robot control typically requires either resource-intensive video generation at test time or…
This study develops an integrated, reproducible design assessment for a four-wheel educational rover intended for the high-school remote-control division of the 2027 NASA Human Exploration Rover…
Prediction models degrade when the deployment population differs from the one used to train them, and training data cannot say which feature-response relationships will transfer. Expert elicitation…
Learning controllable world dynamics from heterogeneous interaction videos is challenging because robot embodiments use incompatible action spaces, while human videos lack native control labels. We…
Mobile robot manipulators extend contact-task capability beyond the workspace of fixed robot installations, but their bases must also sustain the forces generated by the task. On lightweight…