MLINFO COLLECTION
Concept bottleneck models (CBMs) let clinicians inspect and correct skin disease diagnoses through clinical concepts, but only if the concept annotations are reliable. We therefore audit the…
Agents that call tools from a shared catalog can pool what they learn about which tool serves which request. We measure what pooled usage examples do to tool retrieval, reporting separately the…
Few-step autoregressive video generation enables low-latency streaming, yet prevailing training pipelines separate causal adaptation from distribution matching. Recent representation-based…
Diffusion-based audio-visual generation methods typically perform joint denoising of audio and video latents throughout the entire sampling trajectory, repeatedly executing modality-specific…
Reliable traversability estimation is essential for autonomous navigation on unstructured terrain. State-of-the-art approaches typically evaluate traversability from deterministic terrain elevation,…
Bayesian networks for continuous variables often rely on restrictive assumptions: linear Gaussian models lack flexibility to capture nonlinear dependencies, while non-parametric approaches provide…
Humanoid motion-tracking policies can reproduce diverse behaviors, yet connecting independently acquired motions into a continuous sequence remains challenging. Interpolation connects boundary poses…
World models are increasingly used to reduce environment interaction when post-training vision-language-action (VLA) policies with reinforcement learning. Yet they are typically trained to predict…
Vision-language models (VLMs) are increasingly embedded in software systems. Testing them raises two problems.
Lunar rovers will primarily rely on cameras for localization until navigation satellite services are deployed, and will continue to need them afterwards for relative navigation, hazard detection, and…
Complex camera motion is central to visual storytelling, yet translating cinematographic intent into controllable, executable camera trajectories remains challenging. We introduce FilmFlow, an…
Can a small change in wording move an AI model from refusing a sensitive request to acting on it? We test 15 models on the same request to increase the income shown on a pay stub.
Masked diffusion models (MDMs) generate sequences by progressively unmasking tokens, but errors introduced during decoding are typically irreversible. Recent work has shown that iterative correction…
Training-free few-step samplers are often described as nearly quality-lossless under conventional FID/CLIP-style evaluation. It remains unclear whether that conclusion transfers to more realistic and…
Autonomous robotic surgery has drawn increased attention in recent years due to its potential to relieve surgeons of time-consuming, mentally straining, and tedious tasks, particularly during…
We propose AgentDreamer, an agent-guided optimization framework that aligns text instructions with simulated motion through explicit 3D motion planning. Given a text instruction and scene geometry,…
Designing RNA molecules that bind to target protein structures requires generating both an RNA conformation and its bound complex geometry, without assuming a predefined binding site. Existing…
Open-world geographic artificial intelligence (GeoAI) agents can transform public geospatial data into accessible decision support for real-world challenges, but must balance autonomous reasoning…
Faithfully understanding the internal process that occurs as models form their chain of thought is an important problem with the rise in model capabilities. However, this remains challenging due to…
Relighting and novel view synthesis of human portraits are essential in applications such as portrait photography, virtual reality (VR), and augmented reality (AR). Despite recent progress, 3D-aware…
Unmanned aerial vehicles (UAVs) have recently emerged as important remote sensing platforms, and UAV navigation has shown great potential in remote sensing applications. However, existing methods do…
Motion planning is central to robotics, and it is increasingly used to correct the motions proposed by learned planners and policies. In both uses, constraints must hold at every instant of the…
Transactions differ in how their value changes with execution time and relative position. Ethereum's EIP-1559 lets them compete through fee fields, but a fee bid gives no enforceable claim to an…
AI agents increasingly act as analysts whose decision can often be cast as hypothesis tests. Classical tests control the Type I error rate, the probability of rejecting a true null hypothesis, for…