MLINFO COLLECTION
We propose a new generative modeling framework grounded in forward-backward partial differential equations (PDEs). These equations arise naturally in mean-field game (MFG) theory, and are closely…
This paper proposes a refinement to existing vision-based portable pipelines for the recognition of graspable object parts. Such pipelines can effectively support automatic grasp selection and…
Sidewinding is an efficient gait for snake robots to locomote on various terrains, by undulating the backbone curve and shifting the contact segments along it. However, relying solely on undulatory…
Full 3D attention is costly in video Diffusion Transformers. Block-sparse attention reduces this cost by computing only selected attention blocks.
Recently, multi-node inertial measurement unit (multi-IMU) systems have shown promise for robust odometry in legged robots. Multi-IMU fusion can improve legged robot odometry but requires accurate…
Among existing embedding compression approaches, low-rank factorization provides a simple and mathematically principled solution by approximating the embedding matrix with a reduced-rank…
We are the first to give a certified rule for whether unseen data belong in a pretrained model's context or its weights, built on an exact law for their information value. That value, the code length…
Interactive video world models predict how an environment evolves under user actions, but most existing systems assume one controlled agent and one task-specific action interface. We study…
In implicit neural representations (INRs), 3D signals are encoded directly in network weights, making stable weight-space operations essential. However, permutation symmetry causes independently…
3D semantic occupancy prediction estimates voxel-wise occupancy and semantic labels throughout a scene. Our experiments reveal that conventional sparse transposed-convolution upsampling yields poorly…
Practical image generation requires both human preference alignment and few-step efficiency, yet combining reinforcement learning (RL) with distillation is often multi-stage and may erode RL gains We…
Quantization-aware training (QAT) aims to recover reasoning capabilities in low-bit large language models (LLMs). Existing recipes typically supervise the quantized student with the original…
Robots deployed in human-centered environments need maps that support both geometric navigation and open-vocabulary semantic queries beyond a fixed label set. A key challenge is enriching such maps…
EEG foundation models are advancing at an unprecedented pace, yet their evaluation is driven by downstream accuracy, which reveals little about whether their predictions rely on physiologically…
Infrared small target detection (IRSTD) is a challenging task due to the extremely small size of targets, low signal-to-noise ratios, and heavy background clutter in infrared imagery. While the…
Sparse Mixture-of-Experts (SMoE) models improve scalability by routing input tokens to only a subset of expert networks, but they often suffer from representation collapse, in which multiple experts…
A transformer MLP gives each hidden channel two roles: a reader that decides when the channel responds, and a writer that decides what it adds back to the residual stream. Read as a key--value…
User-facing LLM agents must identify which behavioral policies apply at each turn, but evaluating every policy with an LLM is costly. We introduce Signals and Queries (S&Q), a lightweight first-stage…
Accurate localization of neonatal hypoxic--ischemic encephalopathy (HIE) lesions on apparent diffusion coefficient (ADC) images is clinically important but is limited by scarce expert annotations and…
Recent electroencephalography (EEG) foundation models increasingly emphasize model scale, potentially limiting their deployment on resource-constrained devices and in everyday environments. We argue…
Language models are being explored as the interface through which space robots interpret operator commands and select among verified skills. Running them onboard calls for low-bit compression, and…
Finding K most similar elements for a query in a large gallery of neural network (NN) embeddings is essential in various areas of computer science and industrial applications of artificial…
Large language models (LLMs) are increasingly used to support consequential decisions, yet their reliability under equivalent representations of uncertainty remains unclear. Existing work has…
An LLM multi-agent system (MAS) is only as good as the agents it chooses to trust: its accuracy and cost hinge on its topology, meaning which agents are included and how they communicate. A single…