Search: “inference”

arXiv:2609.05399v1 Announce Type: new Abstract: More than a decade in, explainable AI (XAI) for computer vision has assembled a mature toolbox: attribution, feature visualization, concept-based, and c

arXiv:2609.04222v1 Announce Type: cross Abstract: We present GEPARD (Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue), a streaming text-to-speech model for real-ti

arXiv:2609.04799v1 Announce Type: new Abstract: Cooperative rehabilitation enhances engagement, task performance, and social-motor interaction, yet it demands physical co-presence: users must transmit

arXiv:2503.24377v2 Announce Type: replace-cross Abstract: Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitionin

arXiv:2609.05300v1 Announce Type: new Abstract: Safe robot navigation in dense crowds requires reasoning about pedestrian motion and how it may change in response to a robot. However, many learning-ba

arXiv:2609.04559v1 Announce Type: new Abstract: Accurate city-level IP Geolocation is an important enabler for the modern digital ecosystem, underpinning services ranging from local content delivery a

arXiv:2609.04304v1 Announce Type: new Abstract: We present Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data pipeline and training recipe be

arXiv:2609.04852v1 Announce Type: new Abstract: Modern LLM agents operate in persistent workspaces whose accumulated history can exceed both GPU KV capacity and the model's native context window. Exis

LayerStoRm: GLM-5.3-Flash UD-Q4_K_XL (186 GiB) at 1M context on 2× RTX 5090 + 2× RTX 5080 (96 GB VRAM total) using RAM for the pinned experts. LayerStoRm is a (still experimental) MIT-licensed continu

arXiv:2609.04698v1 Announce Type: new Abstract: Vision transformers typically treat every image token as equally important, yet for most tasks in computer vision only a fraction are needed. Adaptive c

arXiv:2609.04262v1 Announce Type: cross Abstract: Spell correction for Japanese search queries presents unique challenges due to the co-existence of four writing scripts (Latin/romaji, hiragana, katak

arXiv:2609.04947v1 Announce Type: cross Abstract: Recently, multimodal large-scale reasoning models have demonstrated remarkable capabilities in solving complex tasks through long Chains-of-Thought (M

arXiv:2404.07124v2 Announce Type: replace-cross Abstract: This paper presents a pipeline designed to bring ultrasound (US) plane pose estimation closer to clinical use, demonstrating the feasibility o

arXiv:2609.04958v1 Announce Type: new Abstract: Recovering camera and hand motion in world coordinates from egocentric video is a key capability for activity understanding, robot learning, and augment

arXiv:2609.04540v1 Announce Type: new Abstract: We introduce Mitra-v2, a tabular foundation model that delivers state-of-the-art performance on real-world classification and regression problems, from

arXiv:2609.05136v1 Announce Type: new Abstract: Time series data is very common in many real-world applications and in numerous domains, with increasing interest for automated information extraction u

arXiv:2609.04250v1 Announce Type: cross Abstract: An avatar that holds a conversation should decide what to say and to move while saying it, yet these abilities live in separate model families: spoken

arXiv:2609.04921v1 Announce Type: cross Abstract: Diffusion probabilistic models can capture the multi-modal, interaction-rich distribution of joint future trajectories in driving scenes. We show that

arXiv:2602.06761v2 Announce Type: replace-cross Abstract: Fetal echocardiography is essential for detecting congenital heart disease (CHD), facilitating pregnancy management, optimized delivery planni

I've built and open-sourced ParaRNN, a PyTorch/Triton library that parallelizes the training of non-linear recurrent architectures across time using Newton-Raphson iterations mapped to associative pre

arXiv:2609.04598v1 Announce Type: cross Abstract: We introduce PetQA, a Korean long-form question-answering (QA) benchmark for evaluating veterinary knowledge and clinical reasoning in large language

arXiv:2609.04516v1 Announce Type: cross Abstract: Recent work on controllable music generation has focused on autoregressive models, leaving diffusion-based systems comparatively underexplored. We pre

arXiv:2609.04808v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to explain and steer language-model behavior, but it remains unclear whether a feature found i

arXiv:2609.04976v1 Announce Type: new Abstract: Personalization models generate new images guided by a few subject references, while style transfer methods aim to produce images aligned with a global

arXiv:2609.04714v1 Announce Type: cross Abstract: Striking a balance between helpfulness and safety remains a fundamental challenge in aligning large language models. To achieve this balance, models s

arXiv:2602.05765v3 Announce Type: replace Abstract: Reinforcement learning (RL) has emerged as a critical paradigm for post-training Vision-Language-Action (VLA) models, enabling embodied agents to ad

arXiv:2609.05323v1 Announce Type: new Abstract: Palynomorphs (microscopic, organic-walled fossils such as pollen, spores, and dinoflagellates) are important high-resolution records of past climates an

arXiv:2609.04886v1 Announce Type: cross Abstract: Changes in sensor height and viewpoint alter object-level point distributions, making cross-platform LiDAR unsupervised domain adaptation (UDA) diffic

arXiv:2609.04264v1 Announce Type: new Abstract: Latent world models have become increasingly popular as a method to predict and plan in latent space rather than pixel space. Recent architectures, such

arXiv:2609.04282v1 Announce Type: new Abstract: Diffusion models have become the mainstream paradigm for modern visual generation and have substantially advanced multimedia content synthesis, especial

⚠️ The most important question hardly anyone is asking is whether Jensen meant 100K+ GPUs, or 100k+ NVLink72 server racks (which contain 72 Blackwell GPUs). ⚠️ From his wording, it sure looks like the

arXiv:2609.04635v1 Announce Type: new Abstract: Neural ocean emulators are being proposed for regional forecasting in cyclone-exposed coastal seas, and a natural design choice is to hand the network t

arXiv:2503.08904v3 Announce Type: replace Abstract: The recent developments in data-driven methods have paved the way to new methodologies to provide accurate state reconstruction of engineering syste

arXiv:2609.05369v1 Announce Type: cross Abstract: Vision-language-action (VLA) models can execute short manipulation skills, but remain brittle in long-horizon procedures requiring persistent task sta

arXiv:2609.04489v1 Announce Type: cross Abstract: Pause-token methods improve LLM reasoning by inserting special tokens into sequences. Prior work explains these gains through computational expressivi

arXiv:2609.04637v1 Announce Type: cross Abstract: Audio Large Language Models (Audio LLMs) have advanced in audio understanding, yet they can still predict the answer by reasoning from textual cues or

arXiv:2609.04575v1 Announce Type: cross Abstract: Modern fine-grained Mixture-of-Experts (MoE) models route each token to a small number of experts and renormalize their router probabilities. We show

arXiv:2609.05415v1 Announce Type: new Abstract: Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Exist

We are excited to bring the first open benchmarking of Google's TPUs to the world Running every day, on many models + scenarios $/token is better than B200 and B300 Huge shout-out to Google @inferact

arXiv:2609.04766v1 Announce Type: cross Abstract: Generative AI research has increasingly evaluated factuality, citation, coverage, and report structure. Yet passing such local checks does not by itse

arXiv:2609.04741v1 Announce Type: new Abstract: Recent zero-shot 3D visual grounding methods leverage vision-language models (VLMs) to localize objects in 3D scenes from natural language queries. Howe

“Currently I believe that no lab has solved alignment and monitoring to a sufficient degree to continue responsibly scaling at maximum speed for much longer. I expect and hope for voluntary slowdowns

Introducing 𝐒𝐩𝐞𝐜𝐮𝐥𝐚𝐭𝐢𝐯𝐞 𝐃𝐞𝐜𝐨𝐝𝐢𝐧𝐠: 𝐇𝐨𝐰 𝐈𝐭 𝐄𝐯𝐨𝐥𝐯𝐞𝐝, 𝐖𝐡𝐞𝐧 𝐈𝐭 𝐒𝐭𝐚𝐲𝐬 𝐋𝐨𝐬𝐬𝐥𝐞𝐬𝐬, 𝐚𝐧𝐝 𝐖𝐡𝐚𝐭'𝐬 𝐍𝐞𝐱𝐭. An interactive tutorial @Madisonkanna and I built for the NeurIPS Education Track. Every LLM you use generate

Reasoning from scratch round 2: In this video, I cover the text generation process in LLMs and KV caching (to prepare the base model before adding reasoning techniques in the upcoming ones). 00:00 Int

Banger paper from Microsoft and Cornell. If you have looked at thinking tokens and decided you cannot afford the context, read this one. (bookmark it) A pause token buys the model extra compute for ea

so does this digital fly have the memory of the real fly that was scanned or what I’ve successfully run the full retained MaleCNS v1.0 fruit fly connectome, all 166,700 neurons, inside Minecraft, with