Looped Diffusion Transformer
arXiv:2609.40305v1 Announce Type: new Abstract: Improving text-to-image models has traditionally relied on increasing model size or the number of denoising steps. In this work, we explore an alternati
Knowledge catalogue
arXiv:2609.40305v1 Announce Type: new Abstract: Improving text-to-image models has traditionally relied on increasing model size or the number of denoising steps. In this work, we explore an alternati
arXiv:2609.40087v1 Announce Type: cross Abstract: Flow-matching approaches to voice conversion (VC) have gained attention owing to their high speech quality and strong speaker similarity. Among them,
arXiv:2609.39273v1 Announce Type: new Abstract: This report presents extbf{MegaAvatar}, a controllable talking avatar generation framework built on top of the Wan2.2-TI2V-5B model. Compared with previ
arXiv:2609.39182v1 Announce Type: cross Abstract: World Models are appearing as the next major frontier in computer vision. However, their robustness is currently largely unexplored. We identify the p
arXiv:2609.38718v1 Announce Type: new Abstract: Steering large language models typically relies on linear, context-independent interventions in activation space, an assumption that recent work has cha
arXiv:2609.39628v1 Announce Type: new Abstract: This paper proposes MIND, a marginal-invariant neural dependency diffusion model for mixed-type tabular data. MIND does not directly learn the joint dis
arXiv:2609.38261v1 Announce Type: cross Abstract: In this paper we propose NinaXander, a series of composed language models obtained by connecting layers of frozen language models from different archi
arXiv:2601.20701v2 Announce Type: replace Abstract: Real-time robot control demands fast action generation. Diffusion and flow matching policies for robot control require multi-step sampling, limiting
arXiv:2609.40358v1 Announce Type: new Abstract: Video world models are expected to predict how the physical world evolves, yet they often produce visually plausible videos that violate basic physical
arXiv:2609.39266v1 Announce Type: new Abstract: Fine-grained vision-language alignment in chest radiography enables zero-shot classification, grounding, and segmentation without task-specific annotati
arXiv:2609.38780v1 Announce Type: cross Abstract: Audio is increasingly used for human activity recognition (HAR) because it captures object interactions, environmental events, and contextual cues in
arXiv:2609.40212v1 Announce Type: new Abstract: This study compared classifiers that differentiate between urbanized and non-urbanized areas based on unmanned aerial vehicle (UAV)-acquired RGB imagery
arXiv:2609.39518v1 Announce Type: new Abstract: Effective human-AI collaboration requires partners to establish references through interaction, which becomes fragile when descriptions are ambiguous, s
arXiv:2609.38538v1 Announce Type: cross Abstract: Random splitting can yield non-independent train--test subsets when a dataset contains related samples, as is common in certain applications such as b
arXiv:2609.35470v1 Announce Type: cross Abstract: Applied researchers increasingly convert images into features with pretrained encoders, then use those features in a downstream prediction model. The
arXiv:2609.39357v1 Announce Type: new Abstract: Asynchronous SGD is a popular algorithm for distributed learning where each client's gradient update is applied on arrival. This leads to a speed-up, bu
arXiv:2609.38980v1 Announce Type: new Abstract: Radar hardware faults threaten automated perception, motivating accurate, compact diagnosis and understandable maintenance guidance. We introduce SCORE-
arXiv:2609.38521v1 Announce Type: cross Abstract: We introduce ShamAN-Q, a sub-1-bit post-training quantization method that extends NanoQuant by replacing each its diagonal reconstruction geometry wit
arXiv:2607.09351v2 Announce Type: replace Abstract: Severe downsampling makes single image super-resolution (SISR) an ill-posed problem, in which the language-guided multi-modal methods are especially
arXiv:2609.39873v1 Announce Type: new Abstract: World action models (WAMs) are large embodied policies that jointly predict future video and the actions to execute, emitting a fixed-length action chun
arXiv:2609.40244v1 Announce Type: new Abstract: Mobile robots and vehicles carry synchronized multi-camera rigs, yet many streaming 3D foundation models are designed for monocular input, leaving effic
arXiv:2609.39807v1 Announce Type: cross Abstract: Lie detection probes aim to predict from a language model's internal states whether its output is truthful or dishonest. However, role-play complicate
arXiv:2609.38537v1 Announce Type: new Abstract: GPT-6 Astra exhibits a remarkable ability to generate numerical robot actions, extending its role beyond high-level planning. To assess Astra's capabili
arXiv:2609.38565v1 Announce Type: new Abstract: Over the past 25 years, sketching and sampling have become widely used tools for accelerating large-scale regression. In iterative randomized solvers, a
arXiv:2609.38205v1 Announce Type: new Abstract: System prompts are the primary lever practitioners use to control language model behavior, yet what they actually do to the computation inside the trans
arXiv:2609.38541v1 Announce Type: new Abstract: Instruction-guided video editing has made significant progress, yet existing methods use multimodal large language models (MLLMs) primarily as semantic
arXiv:2609.39199v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) rely on effective audio encoders for multi-task performance. We introduce UniAE-MoE, a unified audio encoder desig
arXiv:2609.39388v1 Announce Type: cross Abstract: Mobile manipulation requires precise navigation to a manipulation-ready pose followed by reliable object interaction. These two stages differ in actio
arXiv:2602.10124v2 Announce Type: replace-cross Abstract: Cycling is reported by an average of 35% of adults at least once per week across 28 countries, and as vulnerable road users directly exposed t
arXiv:2504.05008v3 Announce Type: replace Abstract: The rapid development of AI-driven tools, particularly large language models (LLMs), is reshaping professional writing. Still, key aspects of their
arXiv:2603.14733v2 Announce Type: replace Abstract: Multimodal Large Language Models have achieved strong performance in single-video understanding, yet their ability to reason across multiple videos
arXiv:2609.37941v1 Announce Type: new Abstract: This study provides a data-driven analysis of a novel dataset of single-cell Anion Exchange Membrane water electrolyzers (AEMWE), operated under constan
arXiv:2609.37041v1 Announce Type: cross Abstract: Self-Distillation Fine-Tuning (SDFT) enables a language model to act as its own teacher: by conditioning on a demonstration, the model produces an imp
arXiv:2609.36097v1 Announce Type: cross Abstract: Using predictive models to explain cognition requires more than accurate behavioral predictions. Input ablations offer an appealing route: remove info
arXiv:2609.35831v1 Announce Type: new Abstract: Modern large language models now support context windows of more than one million tokens, which has raised the question of whether retrieval-augmented g
arXiv:2609.35970v1 Announce Type: cross Abstract: Large language models are able to solve tasks whose answers depend on not only individual input tokens, but also on relations among them. How is such
arXiv:2609.36965v1 Announce Type: new Abstract: System One models such as Jev offer an efficient alternative to generative language models for tasks that require decisions rather than open-ended respo
arXiv:2609.37567v1 Announce Type: cross Abstract: Driven by the rapid advancement of large language models (LLMs), LLM-based multi-agent systems (MAS) have emerged as a powerful paradigm for collabora
arXiv:2501.10162v3 Announce Type: replace-cross Abstract: Optimal transportation of raw material from suppliers to customers is an issue arising in logistics that is addressed here with a continuous m
arXiv:2609.36504v1 Announce Type: new Abstract: Accurate prediction of three-dimensional (3D) microstructure evolution remains computationally demanding because high-fidelity phase-field simulations r
https://preview.redd.it/xs01ds930nsh1.png?width=4800&format=png&auto=webp&s=939762bcf3fbd93e137d4f97e927dda38aaf30fd Back in July I shared LokalBot here. It's a free, open-source Mac app that records
arXiv:2602.08059v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models can reproduce specific artists visual styles at extremely low cost, raising copyright and deployment safety con
arXiv:2609.37145v1 Announce Type: new Abstract: LLM-as-a-Judge is increasingly used to evaluate policy responses on open-ended tasks that lack ground-truth answers. Existing work often directly conver
arXiv:2609.36145v1 Announce Type: new Abstract: Tampered Text Detection (TTD) is essential for safeguarding document authenticity in security-critical workflows. Existing expert models are effective a
Building on nearly a decade of co-engineering, CoreWeave has built NVIDIA compute, networking and software into a cloud purpose-built for AI that’s still returning on investment across multiple genera
arXiv:2609.36115v1 Announce Type: new Abstract: Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-critic
arXiv:2609.37481v1 Announce Type: new Abstract: Large-scale pervasive sensing increasingly relies on high-resolution satellite imagery, yet task-specific onboard vision is constrained by costly annota
arXiv:2609.35793v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR). An exact verifier can also support tes
arXiv:2609.37937v1 Announce Type: new Abstract: How much of an image does a detector need to see? Small RGB regions can retain useful evidence of image synthesis even when they reveal little of the fu
arXiv:2609.37670v1 Announce Type: new Abstract: MeanFlow enables efficient few-step generation by predicting interval-average velocities, but this representation creates a mismatch for reward fine-tun
arXiv:2609.37057v1 Announce Type: new Abstract: Achieving strong performance with graph neural networks (GNNs) typically requires training and hyperparameter tuning for each dataset, incurring repeate
arXiv:2609.37323v1 Announce Type: new Abstract: Discrete diffusion models have emerged as a powerful paradigm for solving combinatorial optimization (CO) problems on graphs by learning to sample high-
I just bought the GPUs after deliberating and debating for over two years. With costs not coming down any time soon and me just wanting to get this massive todo-box ticked, I decided to just YOLO it;
arXiv:2503.03791v1 Announce Type: cross Abstract: Understanding how individual traits influence team performance is valuable, but these traits are not always directly observable. Prior research has in
arXiv:2609.37362v1 Announce Type: new Abstract: Large language model (LLM) routing aims to assign each query to the most suitable model from a heterogeneous candidate pool, improving the quality--effi
arXiv:2609.37588v1 Announce Type: new Abstract: Users of language-based assistive agents often make ambiguous requests. In response, an assistant can either directly act on its interpretation of the r
arXiv:2609.35694v2 Announce Type: replace Abstract: Continuous diffusion generates complete reasoning solutions through iterative refinement in latent space. We introduce the Continuous Embedding Diff
arXiv:2609.36680v1 Announce Type: new Abstract: Visual reprogramming adapts pretrained models to downstream tasks by modifying their input and output interfaces while keeping the backbone fixed. In vi
arXiv:2609.36653v1 Announce Type: new Abstract: Recurrent reasoning models have attracted growing attention for scaling test-time computation, typically by iteratively refining latent states with shar
arXiv:2609.37759v1 Announce Type: cross Abstract: Vision-language models (VLMs) exhibit strong multimodal capabilities but remain vulnerable to backdoors implanted through poisoned fine-tuning data. E