Knowledge catalogue
arXiv:2610.04607v1 Announce Type: cross Abstract: Robots need to anticipate how their actions will change the world, since manipulation success hinges on the resulting contacts and object motions. How
arXiv:2610.05011v1 Announce Type: cross Abstract: Floorplans provide compact and widely available geometric maps for indoor localization, but existing high-performing floorplan-based methods still con
arXiv:2610.05711v1 Announce Type: cross Abstract: Strong image generation models are conditioned on class labels, aligned to frozen pretrained encoders, or built on separately trained autoencoders. Wh
arXiv:2610.06621v1 Announce Type: new Abstract: Spectral variants of low-rank adaptation (LoRA) choose both a subspace and which factor to freeze. We separate these choices by freezing the input facto
arXiv:2610.05563v1 Announce Type: cross Abstract: Small language model (SLM) agents need safety controls that track consequences across tool calls with little monitoring overhead. A private read, for
arXiv:2610.04033v1 Announce Type: cross Abstract: Information and infectious diseases spread through social networks, but the spreading probabilities driving them are hard to estimate without per-node
arXiv:2610.04390v1 Announce Type: cross Abstract: Simulation-free training of latent Stochastic Differential Equations (SDEs) relies on a variational posterior process whose one-time marginals are tra
arXiv:2610.05599v1 Announce Type: cross Abstract: Temporal dependence can separate the Gaussian approximation of stochastic gradient descent from its stationary moments. For unmodified least-squares S
arXiv:2406.07579v2 Announce Type: replace-cross Abstract: 2D irregular packing is a classic combinatorial optimization problem with various applications, such as material utilization and texture atlas
arXiv:2511.07734v2 Announce Type: replace Abstract: Bayesian optimization (BO) is a powerful framework for optimizing expensive black-box objectives, yet extending it to graph-structured domains remai
Great report from Google and MIT. Co-designing ML models and the accelerators is an exciting research direction. This report introduces Coco, an agent platform TPU architects use for hardware and mode
arXiv:2610.04651v1 Announce Type: cross Abstract: Neural audio codecs compress waveforms into compact discrete tokens that underpin speech language models, real-time communication, and large-scale aud
arXiv:2610.05139v1 Announce Type: new Abstract: Code large language model (Code LLM) assistants generate code from heterogeneous development contexts, including open files, imported modules, pasted sn
arXiv:2610.06677v1 Announce Type: new Abstract: Mixture-of-experts (MoE) routers typically apply softmax to the router scores and keep the top-K experts, making every token use exactly K experts. Spar
arXiv:2610.04238v1 Announce Type: cross Abstract: Humanoid robots could transport payloads substantially heavier than themselves by pulling passive wheeled vehicles instead of carrying the load. This
arXiv:2511.18199v2 Announce Type: replace-cross Abstract: Ecological Momentary Assessment (EMA) studies provide real-time data on suicidal thoughts and behaviors, but forecasting suicide attempts rema
arXiv:2312.01886v4 Announce Type: replace Abstract: Large vision-language models (LVLMs) have demonstrated their incredible capability in visual question answering. However, this rich visual interacti
arXiv:2610.04727v1 Announce Type: new Abstract: In worker-equipment proximity monitoring, video transformers are widely used for collision anticipation and have demonstrated strong performance. Howeve
arXiv:2610.06234v1 Announce Type: new Abstract: Multi-instance partial-label learning (MIPL) addresses inexact supervision in both the instance and label spaces, which can be applied to video classifi
arXiv:2610.06023v1 Announce Type: new Abstract: Exploiting meaningful latent structures from data to solve downstream tasks is a fundamental challenge in signal processing and machine learning. While
arXiv:2610.05306v1 Announce Type: new Abstract: Sign language-text alignment remains a fundamental challenge for text-driven sign language understanding. Existing methods predominantly rely on appeara
arXiv:2610.03842v1 Announce Type: new Abstract: Knowledge distillation is crucial for deploying vision-language models on resource-constrained devices. However, existing methods typically impose unifo
arXiv:2508.17512v2 Announce Type: replace Abstract: Differentiable logic networks (DLNs) have shown promising results in tabular domains by combining accuracy, interpretability, and computational effi
arXiv:2610.05879v1 Announce Type: cross Abstract: We present the Prior-Fitted Language Model (PFLM), a 300M-parameter byte-level transformer pretrained only on samples from a synthetic non-linguistic
arXiv:2610.05024v1 Announce Type: new Abstract: Aerial vision-and-language navigation (VLN) enables unmanned aerial vehicles to execute long-horizon natural-language instructions from visual observati
arXiv:2610.04351v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) increasingly aggregates multi-view evidence with heavy learned 3D networks. We propose LoCoSplat (Local-Contex
arXiv:2610.05265v1 Announce Type: new Abstract: Looped language models provide a parameter-efficient way to scale iterative test-time computation by repeatedly executing a shared recurrent core. Post-
arXiv:2610.04036v1 Announce Type: new Abstract: Vision Transformers (ViTs) have shown strong performance in volumetric segmentation, but their effectiveness on clinical CT is limited by an isotropic E
arXiv:2610.04963v1 Announce Type: new Abstract: Graph few-shot class-incremental learning (GFSCIL) requires a model to continually recognize emerging classes from only a few labeled nodes while preser
Malware reverse-engineering: solving an out-of-distribution investigation task. When faced with an unknown binary, Mistral Large 4 reverse-engineers it end-to-end. In this case, it concludes the sampl
arXiv:2610.04510v1 Announce Type: cross Abstract: Diffusion models for structured scientific generation must produce samples satisfying hard geometric constraints imposed by physics, chemistry, or bio
arXiv:2610.06510v1 Announce Type: new Abstract: When searching for an object, people choose their next move by considering both likely target locations and places already explored. The current view ca
arXiv:2610.04422v1 Announce Type: new Abstract: Guided diffusion samplers are increasingly used to reconstruct physical fields from sparse observations, but standard diagnostics do not say how much of
Microsoft confirms on publicly accessible web page that OpenAI has been using Looped Transformers in the GPT-6 series, proving The Information's reporting was correct all along. GPT-6.1 Sol uses 2 inf
arXiv:2610.05289v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have achieved remarkable performance in novel view synthesis, yet deploying both static and dynamic Gaus
arXiv:2510.16587v2 Announce Type: replace-cross Abstract: Understanding the continuous evolution of populations from discrete temporal snapshots is a critical research challenge, particularly in field
arXiv:2610.05081v1 Announce Type: new Abstract: Teleoperation is becoming increasingly important for collecting high-quality demonstrations to teach robots dexterous manipulation skills. For dexterous
arXiv:2610.04155v1 Announce Type: cross Abstract: Open electromagnetic-transient datasets are beginning to make reproducible learning-based protection studies possible, but the practical use of these
arXiv:2610.04454v1 Announce Type: new Abstract: Recently, Drifting Models and Wasserstein Gradient Flows have attracted substantial attention because they move iterative distributional refinement to t
arXiv:2503.19945v4 Announce Type: replace-cross Abstract: Mammography, an X-ray-based imaging technique, remains central to the early detection of breast cancer. Recent advances in artificial intellig
arXiv:2610.04602v1 Announce Type: new Abstract: Primitive-based 3D segmentation offers a compact and explicit alternative to dense surface prediction, naturally supporting structural abstraction and b
arXiv:2610.04616v1 Announce Type: cross Abstract: A vision--language--action (VLA) policy can complete complex tasks while ignoring the evidence that should determine its actions. An object held near
arXiv:2610.05004v1 Announce Type: new Abstract: Full-wave electromagnetic (EM) simulation enables accurate patch-antenna analysis but is computationally expensive for large-scale forward prediction an
arXiv:2610.05699v1 Announce Type: new Abstract: The efficacy of traditional disease prediction is limited by spatial gaps and temporal lags, which impact the timing and targets of resource deployments
arXiv:2604.01142v2 Announce Type: replace-cross Abstract: Reinforcement learning has shown strong performance in robotic manipulation, but learned policies often degrade in performance when test condi
arXiv:2610.03972v1 Announce Type: new Abstract: Ising machines have emerged as promising hardware accelerators for intractable optimization and sampling problems, yet their practical impact increasing
arXiv:2610.06076v1 Announce Type: cross Abstract: Preparing quantum states from classical data can cost more than the computation they serve; most loaders tailor a circuit to each input. Here we show
arXiv:2610.04913v1 Announce Type: new Abstract: World Action Models (WAMs) emerge as a promising foundation for policy refinement by predicting the consequences of sampled actions. However, visually p
arXiv:2603.05925v2 Announce Type: replace Abstract: In this paper, we propose a Rectified Flow Auto Coder (RAC) inspired by Rectified Flow to replace the traditional VAE: 1. It achieves multi-step dec
arXiv:2610.04406v1 Announce Type: new Abstract: Safe robot control often requires combining long-horizon performance optimization with hard state and input constraints, but existing approaches tend to
arXiv:2610.06324v1 Announce Type: new Abstract: CLIP-like vision-language models remain a cornerstone of multimodal systems, yet their scores stay near chance on directed spatial relations, such as wh
arXiv:2610.05185v1 Announce Type: new Abstract: GUI grounding is a critical capability for GUI agents powered by vision-language models, helping them execute user instructions by locating the correspo
arXiv:2510.16444v2 Announce Type: replace Abstract: Who is being described, where are they, and what are they doing? Referring Atomic Video Action Recognition (RAVAR) answers these questions jointly b
releasing my local AI slide deck covers from prefill vs decode, MoE vs dense, VRAM vs unified memory, quantization to speculative decoding, everything with llama.cpp feel free to reuse with attributio
arXiv:2610.04272v1 Announce Type: new Abstract: Combining capabilities of multiple expert models trained starting from the same base checkpoint has become increasingly common in frontier language-mode
arXiv:2610.03858v1 Announce Type: new Abstract: We investigate a general-purpose layer for deep learning that, instead of compressing arbitrary-size training data into fixed-size weight matrices, stor
arXiv:2610.04741v1 Announce Type: new Abstract: Force-aware manipulation typically relies on specialized force or tactile sensors. We show that force-aware manipulation can instead be achieved through
arXiv:2503.21969v4 Announce Type: replace Abstract: Robotic long-horizon manipulation requires robots to compose perception, reasoning, and action over extended task sequences, yet existing language-c
arXiv:2610.04091v1 Announce Type: new Abstract: Signal separation problems are common in science. A prominent example of this occurs during the use of diffraction or spectroscopy to identify the indiv
arXiv:2610.04457v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve strong performance on image recognition and mobile vision applications, but their high-dimensional linear projections