Knowledge catalogue
arXiv:2604.16587v1 Announce Type: new Abstract: We present an amortized framework for real-time visual attribution streaming in multimodal thinking models. When these models generate code from a scree
arXiv:2604.17289v1 Announce Type: new Abstract: Supervised fine-tuning of large language models relies on human-annotated data, yet annotation pipelines routinely involve multiple crowdworkers of hete
arXiv:2604.18307v1 Announce Type: new Abstract: Language models often solve complex tasks by generating long reasoning chains, consisting of many steps with varying importance. While some steps are cr
Priority Technologies: Ensuring US Security and Shared ProsperityEdited by Elisabeth B. Reynolds, professor of the practice of urban studies and planning and former executive director of the MIT Task
arXiv:2604.17578v1 Announce Type: new Abstract: Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirica
arXiv:2604.16734v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual in
arXiv:2604.16850v1 Announce Type: new Abstract: Fast execution of contact-rich manipulation is critical for practical deployment, yet providing fast demonstrations for imitation learning (IL) remains
arXiv:2509.01082v3 Announce Type: replace Abstract: Probabilistic programming offers a powerful framework for modeling uncertainty, yet statistical model discovery in this domain entails navigating an
arXiv:2604.17222v1 Announce Type: new Abstract: Breast cancer diagnosis demands rapid and precise tools, yet traditional histopathological methods often fall short in intra-operative settings. Deep Ul
arXiv:2510.23116v3 Announce Type: replace Abstract: Diffusion bridge models establish probabilistic paths between arbitrary paired distributions and exhibit great potential for universal image restora
arXiv:2506.02541v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) can recognize individuals in images and disclose sensitive personal information about them, raising criti
arXiv:2601.02735v2 Announce Type: replace Abstract: Decision forests induce supervised similarities through the partition structure of their trees. Yet forest proximity computation is still often trea
arXiv:2604.16384v1 Announce Type: new Abstract: We present RHINO-AR, an interactive Augmented Reality (AR) museum exhibit that reintroduces the historical mobile robot RHINO into its original exhibiti
arXiv:2604.17341v1 Announce Type: new Abstract: Diabetic retinopathy (DR) is a leading cause of vision impairment worldwide, and automated grading systems play a crucial role in large-scale screening
Listen to the session or watch below Watch a special edition of Roundtables simulcast live from EmTech AI, MIT Technology Review’s signature conference for AI leadership. Subscribers got an exclusive
Russia eased vaccination standards when diphtheria seemed beaten. 157,000 infections. 5,000 dead. Japan dropped mandates after a trust collapse. Rubella came back. Babies born blind and deaf. Nigeria
arXiv:2604.16453v1 Announce Type: new Abstract: We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding m
arXiv:2604.16445v1 Announce Type: cross Abstract: Recent advances in Artificial Intelligence (AI) and the exploration of noninvasive, objective biomarkers, such as speech signals, have encouraged the
arXiv:2604.18312v1 Announce Type: new Abstract: We address the problem of planning in an environment with deterministic dynamics and stochastic rewards with discounted returns. The optimal value funct
arXiv:2604.16535v1 Announce Type: new Abstract: Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved thr
arXiv:2604.17147v1 Announce Type: new Abstract: We introduce ScenarioControl, the first vision-language control mechanism for learned driving scenario generation. Given a text prompt or an input image
arXiv:2604.17734v1 Announce Type: new Abstract: Cryo-electron microscopy (cryo-EM) enables single-particle analysis of biological macromolecules under strict low-dose imaging conditions, but the resul
arXiv:2602.19549v2 Announce Type: replace Abstract: Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current
arXiv:2604.17433v1 Announce Type: new Abstract: Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but
arXiv:2506.10137v3 Announce Type: replace Abstract: While goal-conditioned behavior cloning (GCBC) methods can perform well on in-distribution training tasks, they do not necessarily generalize zero-s
arXiv:2604.17652v1 Announce Type: new Abstract: Sentinel-5P (S5P) plays a critical role in atmospheric monitoring; however, its spatial resolution limits fine-scale analysis. Existing super-resolution
arXiv:2604.18237v1 Announce Type: new Abstract: In large-scale distributed scenarios, increasingly complex tasks demand more intelligent collaboration across networks, requiring the joint extraction o
arXiv:2604.17659v1 Announce Type: new Abstract: We introduce the Semantic Density Effect (SDE): the empirical finding that prompts carrying higher semantic information per token consistently produce m
Sen. Warren: 'Did Donald Trump lose the 2020 election?' Handsome Kevin: 'ummm... errr... ' His response raises real questions about whether Warsh is independent of the President and if he has the cour
arXiv:2505.13353v4 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed for understanding large codebases, but whether they understand operational semantics of long
arXiv:2604.02908v2 Announce Type: replace Abstract: We present SentiAvatar, a framework for building expressive interactive 3D digital humans, and use it to create SuSu, a virtual character that speak
arXiv:2604.18580v1 Announce Type: cross Abstract: Modern sequence models are dominated by Transformers, where self-attention mixes information from the visible context in an input-dependent way. Howev
arXiv:2604.16842v1 Announce Type: cross Abstract: This thesis develops numerical and theoretical approaches for understanding and analyzing singularity formation in Partial Differential Equations (PDE
arXiv:2604.16517v1 Announce Type: cross Abstract: Large vision-language models (VLMs) achieve strong performance on multimodal tasks but often suffer from hallucination and poor grounding in knowledge
arXiv:2505.13660v2 Announce Type: replace-cross Abstract: This paper introduces a new constraint-free concave dual formulation for the Wasserstein barycenter. Tailoring the vanilla dual gradient ascen
arXiv:2406.06543v2 Announce Type: replace-cross Abstract: Deep learning has driven significant technological advancements, but its high energy consumption limits its use on battery-operated edge devic
arXiv:2506.18141v3 Announce Type: replace Abstract: We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (S
arXiv:2604.17385v1 Announce Type: new Abstract: Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge fo
arXiv:2604.17287v1 Announce Type: new Abstract: Copy-move forgery, where a region within an image is duplicated to hide or fabricate content, remains a persistent threat to visual media integrity. We
arXiv:2604.17397v1 Announce Type: new Abstract: Autoregressive video diffusion is emerging as a promising paradigm for streaming video synthesis, with step distillation serving as the primary means of
arXiv:2512.21204v2 Announce Type: replace Abstract: Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compar
arXiv:2511.05152v2 Announce Type: replace Abstract: Deformable Gaussian Splatting (GS) accomplishes photorealistic dynamic 3-D reconstruction from dense multi-view video (MVV) by learning to deform a
arXiv:2511.11391v3 Announce Type: replace Abstract: Phase-time arrays, which integrate phase shifters (PSs) and true-time delays (TTDs), have emerged as a cost-effective architecture for generating fr
arXiv:2604.16607v1 Announce Type: new Abstract: With the rise of generative language models, machine-generated text detection has become a critical challenge. A wide variety of models is available, bu
arXiv:2604.17068v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) enable parallel text generation by iteratively denoising a fully masked sequence, unmasking a subset of masked t
arXiv:2601.04052v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously
arXiv:2506.08013v2 Announce Type: replace Abstract: Multi-task learning for dense prediction is limited by the need for extensive annotation for every task, though recent works have explored training
arXiv:2604.16774v1 Announce Type: new Abstract: Long-horizon language model systems increasingly rely on persistent memory, yet many current designs still treat memory primarily as a static store: wri
arXiv:2604.17611v1 Announce Type: new Abstract: Parkinson's disease (PD) is a progressive disorder in which symptom burden and functional impairment evolve over time, making severity staging essential
arXiv:2602.11528v2 Announce Type: replace-cross Abstract: Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generate
arXiv:2604.17381v1 Announce Type: cross Abstract: This paper proposes StrEBM, a structured latent energy-based model for source-wise structured representation learning. The framework is motivated by a
This paper presents a prompting technique called 'String Seed of Thought' that enables large language models to generate outputs that are both faithful to underlying data distributions and maintain di
arXiv:2604.16947v1 Announce Type: cross Abstract: This work introduces Structured 3D-SVD as a practical framework for the reconstruction, compression, and analysis of biological volumetric data. Inspi
arXiv:2604.18251v1 Announce Type: new Abstract: In this paper, we present three neural network architectures designed for real-time classification of weather conditions (sunny, rain, snow, fog) from i
arXiv:2510.02025v4 Announce Type: replace Abstract: We introduce a constraint-selection-based experiment design for measuring narrative preferences of Large Language Models (LLMs). This design offers
arXiv:2604.17551v1 Announce Type: new Abstract: Standard approaches to goal-conditioned reinforcement learning (GCRL) that rely on temporal-difference learning can be unstable and sample-inefficient d
arXiv:2604.17830v1 Announce Type: new Abstract: Traditional Task and Motion Planning (TAMP) systems depend on physics models for motion planning and discrete symbolic models for task planning. Althoug
arXiv:2604.18310v1 Announce Type: cross Abstract: Variational inference (VI) is a central tool in modern machine learning, used to approximate an intractable target density by optimising over a tracta
arXiv:2603.18361v2 Announce Type: replace Abstract: Conversational agents are required to respond to their users not only with high quality (i.e. commonsense bearing) responses, but also considering m
arXiv:2508.11184v2 Announce Type: replace Abstract: Distractors-incorrect yet plausible answer choices in multiple-choice questions (MCQs)-are vital in educational assessments, as they help identify s