MLINFO COLLECTION
Diffusion Transformers (DiTs) achieve high-fidelity image and video generation, but they suffer from substantial inference costs due to repeated transformer evaluations across many denoising steps.…
We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision…
Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a…
Brain encoding models aim to predict neural responses to stimuli. The most widely used approach fits readouts from frozen pretrained backbones.
Expert human readers process large inputs (e.g., code repositories and long documents) by skimming to closely read only what matters. On the other hand, language models process all input tokens…
Video face swapping transfers the reference identity to a target video while preserving its other attributes and motion. Despite recent progress in reference-guided flow-based methods, jointly…
Reconstructing human activity from egocentric video requires more than recovering individual 3D components: the observer's motion, surrounding geometry, and hand-object interactions must fit together…
Drafting an answer allows a reasoning model to reconsider each decision in the context of the others. Yet repeated diffusion denoising does not ensure that individually plausible token updates form a…
Lifelong agents continually accumulate and reuse experience to improve after deployment, yet in practice they often operate under tight generation, interaction, and memory budgets. Under such…
Expanding the vocabulary of conditional text-to-speech (TTS) models typically requires extensive fine-tuning with paired audio, creating a major bottleneck for low-resource and cross-lingual…
An effective visual tokenizer must preserve image fidelity while producing latents that downstream diffusion models can learn efficiently. Prior work improves latent diffusability through semantic…
Graphical User Interface (GUI) agents increasingly act over streaming omni-modal observations spanning screenshots, audio, video, interaction history, and device states. However, exposing this…
Generalizing real-time physics-based animation across diverse 3D shapes and spatial discretizations remains challenging. In this paper, we introduce PhysSkin++, a physics-informed framework that…
Training high-quality diffusion models is computationally expensive, and inference-time guidance often adds further sampling cost. In this work, we introduce Swift, a simple yet effective self-guided…
Diffusion language models can write several tokens in one forward pass, and they decide during generation how many passes to spend. Two outputs of the same token length can therefore vary a lot in…
Streaming video world models generate the future chunk by chunk, conditioned on their own past and a stream of actions. Trained on short clips, they drift once a rollout exceeds the training horizon,…
The non-iterative conditional expectation (NICE) plug-in estimator of the g-formula can be used to estimate the causal effects of sustained treatment strategies, even in the presence of…
Over-fitted Gaussian mixtures can contain many parameter configurations with nearly the same density, making the order of density cancellation central to their parameter-learning rates. Ho and Nguyen…
Public charging of electric vehicles (EVs) adds a large and synchronized load to the distribution feeders. In most networks, it is rare to overload a feeder at the same time.
Indirect and noisy observations are difficult to invert when the forward operator smooths out the unknown signal. In this case, the unstable modes are precisely the modes that the data reveals least,…
We study robust estimation of a Gaussian precision matrix that decomposes as a sparse matrix minus a symmetric, possibly indefinite, low-rank matrix, a structure that arises when latent-variable…
In decentralized federated learning, heterogeneous clients may develop complementary expertise, yet each query is typically evaluated only by the client where it arrives. To exploit this distributed…
Candidate-scoring decision models return a probability distribution over a presented set of answers. Public documentation of one such system, Jev, and of an open counterpart, JevAny, describes three…
Ranking data in modern applications often involves covariate vectors whose dimension grows with the number of objects. Identifying relevant covariates and integrating them with item-specific…