MLINFO COLLECTION
Digital SRAM compute-in-memory (CIM) macros enable energy-efficient CNN inference by eliminating off-chip weight transfers; however, peripheral control logic introduces three inefficiencies: bit-…
Traffic forecasting requires modeling complex temporal dynamics and the spatial dependencies imposed by road topology. Supervised graph-based models achieve strong performance, but are often trained…
Threading a quadrotor through a moving narrow gap is a demanding test of agile flight, requiring centimeter-level spatial alignment and precise temporal execution. We address this challenge using a…
Imitation policies that reliably execute most of a manipulation trajectory can still fail in localized regions requiring last-mile precision. Updating the full policy or exploring residual actions…
A joint of pipe run into the hole swings from the elevator over the well and strikes a fixed stabbing guide at whatever speed the swing has. StabBot, a robotic stabbing system, predicts the swing and…
Online resource allocation faces two coupled challenges: (1) allocating scarce resources efficiently under uncertain future demand, and (2) ensuring that agents report task valuations and…
The items of a reflective psychometric scale can be read as a proposal about a construct's structure. Language models make that proposal measurable by converting each item into an embedding, a list…
Fine-tuning Large Language Models (LLMs) on instruction data can quietly erode their safety, even when no training example looks harmful. Because this safety-degrading data looks benign, standard…
Quickest detection problems (QDPs) arise in a wide range of applications. However, the complementarity structure of the associated variational inequalities poses substantial challenges for…
Electric-field-based actuators and machines lead the design space at the nanoscale and in biological systems, while having the potential to be used in favorable macroscale applications which…
Graph neural networks (GNNs) rely critically on neighborhood aggregation, yet conventional mean aggregation may fail to capture class-relevant distributional information, particularly in heterophilic…
Visual world models increasingly support spatial reasoning by generating RGB views of unobserved states. However, RGB has become the default interface largely because it is well suited for visual…
Modern simulators can generate synthetic camera and LiDAR data with accurate annotations for downstream tasks. In contrast, automotive radar simulation remains less mature because it requires not…
Language model performance depends strongly on the mixture of domains in the pretraining data corpus. Popular data mixing methods select these domain weights by training many small proxy models on…
Vision--Language--Action (VLA) models generate robot actions from visual observations and language instructions, but their understanding of physical dynamics remains limited. Video world models can…
Fact-checking explanations help Web users understand why a claim receives its verdict, yet the same explanation may not satisfy readers with different backgrounds and preferences. We formulate…
Vision-Language-Action (VLA) models integrate high-level reasoning with low-level action execution for end-to-end robotic control. However, most VLA models target static manipulation in unconstrained…
We present EmbeddingGemma 2, an open multimodal embedding model which natively represents text, images, audio, video, and combinations thereof in a unified space. Our approach introduces improvements…
Vision-language-action (VLA) models provide a promising paradigm for scalable robotic manipulation, yet their reliance on success-only behavioral cloning leaves them brittle; lacking corrective…
This work investigates the use of event-based spiking controllers, implemented as spiking neural networks, for trajectory tracking in underactuated robots. Specifically, we address the problem of…
Reliable evaluation of inter-annotator agreement (IAA) is important for assessing the consistency of annotation processes. While established IAA metrics such as Cohen's kappa, Fleiss' kappa, and…
Proprietary language models and their reasoning traces are vulnerable to API-based distillation, where an adversary trains a student model on the teacher model's outputs. To obtain evidence of…
Detecting harmful content in Arabic is challenging because of dialectal variations and the semantic overlap between different harm categories. This paper presents a two-stage approach for classifying…
Vision-Language-Action (VLA) policies demonstrate remarkable semantic generalization, yet remain highly vulnerable to out-of-distribution (OOD) visual shifts during execution. While existing…