MLINFO COLLECTION
Why large language models trained via log-loss minimization over massive and diverse datasets exhibit broad capabilities and generalizable skills is not yet fully understood. Grau-Moya et al.
Radar heart sounds capture cardiac mechanical activity without contact, while echocardiography characterizes ventricular and valvular function. Paired measurements connect these signals to structural…
One-step generative models enable fast text-guided image editing, yet they often introduce unintended changes to regions that should remain unchanged. Temporal aggregation stabilizes editing fields…
Thermal cameras enable robots to perceive human activities in darkness while revealing less personally identifiable appearance information and fewer details of the surrounding environment than RGB…
In this paper, we investigate why vision-language models (VLMs) produce errors by decomposing them into two sources: visual-representation failures, in which the visual evidence required for the…
Speculative decoding uses a target model to verify a tree of draft tokens in parallel. We study whether the resulting next-token distributions can help select the next tree.
Retargeting human motion to humanoids requires preserving motion semantics while accounting for the robot's physical constraints. Kinematic pipelines prescribe a robot trajectory through geometric…
Traditional robotic navigation systems separate mapping, planning, and low-level control through cascaded modules, introducing computational overhead and accumulated latency. End-to-end reinforcement…
Vision-based insertion requires correcting alignment errors while retaining useful behavior learned from demonstrations. We present ACT--Flow, an online learning framework that couples an adaptive…
World models predict how embodied systems evolve under actions, but their accuracy can degrade when physical conditions move outside the training distribution. We study two components of causal…
Dropout and zoneout are routinely added to long short-term memory (LSTM) and gated recurrent unit (GRU) networks, but, to our knowledge, their placements have not been crossed with gate…
We introduce OvisOCR3, a 0.8B model for a broad range of OCR-related tasks. OvisOCR3 unifies document parsing, general OCR, key information extraction (KIE), document figure captioning, and…
Diffusion language models form answers through a sequence of revisable continuous states, but multi-agent systems usually discard those states and make agents communicate only after decoding text. We…
Selecting intermediate features from a frozen diffusion model for discriminative tasks is non-trivial because the useful signal is distributed across the denoising trajectory, network depth, and…
Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model often requires domain…
Game engines and coding agents can specify the layout, motion, and camera of a scene, yet turning such coarse structure into realistic video requires a renderer that follows the structure and…
In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1,…
Continuous flow language models offer a path to parallel generation with tools for control and acceleration unavailable to discrete diffusion, yet effective techniques for building them at the…
Practitioners use reinforcement learning methods for language models through training frameworks, so a method that a framework includes is one configuration change away for its users. We measure how…
Moving from controllable videos to genuinely playable worlds requires persistent world state, executable game rules, and low-latency interaction. We outline a roadmap for the next generation of…
Feed-forward 3D Gaussian Splatting (FF3DGS) reconstructs 3D scenes from images in a single forward pass, making it well-suited to applications that must operate within limited resource budgets. To…
Looped language models can run more iterations at test time, but additional iterations need not help them solve longer problems. For sequential state tracking, final-answer supervision does not…
As model parameters scale up, sparsely activated Mixture-of-Experts (MoE) approaches have become essential for model scaling. However, mainstream models currently adopt hierarchical architectures,…
On-policy distillation (OPD) can succeed with surprisingly few training questions, motivating a view of questions as carriers of distributional knowledge transfer. How can we assess whether a newly…