Knowledge catalogue
arXiv:2609.34412v1 Announce Type: new Abstract: Natural-language manipulation instructions specify qualitative relations, whereas continuous controllers require state-evaluable task quantities, differ
arXiv:2609.33983v1 Announce Type: cross Abstract: Semantic Textual Similarity (STS) methods assume that a document's lexical content faithfully represents what it asserts. This assumption fails for di
arXiv:2609.33659v1 Announce Type: new Abstract: Multimodal large language models can expose task-relevant evidence through generation, but producing useful evidence does not by itself determine how it
arXiv:2607.17511v2 Announce Type: replace Abstract: Large Time Series Foundation Models (TSFMs) demonstrate strong zero-shot forecasting capabilities across diverse domains. However, their application
arXiv:2609.33383v1 Announce Type: cross Abstract: The local linear minimization oracle (Ferris and Zavriev, 1996; arXiv:2605.08850), or Local LMO, solves constrained convex problems without having to
arXiv:2609.32854v1 Announce Type: new Abstract: Deep Differentiable Logic Gate Networks (LGNs) and Lookup Table Networks (LUTNs) offer a promising approach for very low power inference due to their us
arXiv:2609.33790v1 Announce Type: cross Abstract: Conventional reflectance photoplethysmography (PPG) typically reduces tissue optical responses to one or a few detector channels. Matrix Pinhole Image
arXiv:2609.35168v1 Announce Type: new Abstract: Saved checkpoints record states along a training trajectory, but generally do not determine the updates at states that would be visited under a differen
arXiv:2609.33895v1 Announce Type: new Abstract: In diffusion-based generation, a neural network can be trained to predict the clean data, the noise, or the velocity from a noisy input. These predictio
arXiv:2609.34004v1 Announce Type: new Abstract: Equity-relevant news evolves through temporally dependent corporate events, making historical information useful only when event continuity, information
arXiv:2609.34210v1 Announce Type: new Abstract: Coding agents are beginning to move beyond purely digital tasks to tackle physical-world challenges, particularly in robotics. Existing robotics benchma
arXiv:2609.32529v1 Announce Type: new Abstract: Open-prompt detectors allow users to specify targets with text, visual exemplars, or both. We argue that existing designs underuse the visual modality i
arXiv:2609.35465v1 Announce Type: new Abstract: Leech-lattice quantization gives good quality at two bits per weight, but its codebooks hold more than 10^14 points, too many for a lookup table. Our ea
arXiv:2609.31747v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) must balance local detail against scene context when interpreting ultra-high-resolution (UHR) remote sensing (R
arXiv:2609.34667v1 Announce Type: cross Abstract: Fine-tuning pre-trained models on specialized tasks with scarce data is central to modern deep learning. Despite its empirical success, theoretical un
arXiv:2609.32518v1 Announce Type: new Abstract: Distilling bidirectional multi-step video diffusion transformers into few-step causal models has become a common approach for streaming video generation
arXiv:2609.33603v1 Announce Type: new Abstract: Reliable optical chemical structure recognition (OCSR) is essential for building high-quality chemical data from scientific literature, yet even small r
arXiv:2509.23219v2 Announce Type: replace Abstract: Technical-domain benchmarks constructed from arXiv papers can overlap the same public text used in LLM pretraining. Auditing this risk at training-c
arXiv:2609.34606v1 Announce Type: new Abstract: Leveraging the paradigm of autoregressive diffusion, text-conditioned interactive video world models aim to simulate temporally coherent environments gu
arXiv:2012.02655v4 Announce Type: cross Abstract: In this article, we define a new non-archimedean metric structure, called cophenetic metric, on persistent homology classes of all degrees. We then sh
arXiv:2609.31395v1 Announce Type: cross Abstract: Agentic LLM inference accumulates long KV caches across iterative observation-reasoning-action loops, imposing substantial memory overhead and limitin
Utkarsh Shetti / Reuters: AI agent startup Instinct raised a 1B Series C from Sequoia, Benchmark, and Coatue at a 10B valuation and details recent products, such as a concierge service — AI agent firm
arXiv:2609.31482v1 Announce Type: new Abstract: Generative AI is reshaping the cultural infrastructures through which knowledge is found, synthesized, and held accountable. To make sense of this shift
context : do not re-reserve the scheduler when toggling causal_attn (#28751) context : do not re-reserve the scheduler when toggling causal_attn llama_context::set_causal_attn() marks the scheduler to
arXiv:2609.30471v1 Announce Type: cross Abstract: Reference-based LLM-as-a-judge evaluation assumes the reference answer is the target. In deployed agentic systems that operate over dynamic entities (
arXiv:2609.31418v1 Announce Type: new Abstract: A photorealistic 3D view tells a teleoperator where a robot is, but not what the scene contains, how well each object has been observed, or how to turn
arXiv:2609.30461v1 Announce Type: new Abstract: Off-road traversability is direction-dependent and vehicle specific, yet most global maps assign a single isotropic cost to each location. Existing lear
Whether you are mapping global forest cover, detecting changes in the built environment, or monitoring agricultural yields, writing scripts in Google Earth Engine is a powerful way to develop these in
arXiv:2502.02707v5 Announce Type: replace Abstract: Multiple Instance Learning (MIL) for whole slide image (WSI) analysis in computational pathology often neglects instance-level learning as supervisi
arXiv:2609.31135v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to localize the spatio-temporal tube in a video corresponding to a natural language query. While recent me
arXiv:2504.06188v3 Announce Type: replace Abstract: AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, part
arXiv:2609.30402v1 Announce Type: cross Abstract: Multimodal misinformation is increasingly crafted to look convincing by pairing a textual claim with an image that appears to 'prove' it. Yet in pract
On Friday I gave the closing keynote at the WeAreDevelopers World Congress North America in San Jose. I tied together the key trends from the past year into a chronological exploration of everything t
hexagon: support for backend sampler (#29502) hex-topk: trying to improve/cleanup the pipeline hex-sampling: add STEP op hex-sampler: add SUM op hex-sampler: update CPY to support sampling cases hex-b
Elliot Arledge released a video titled “Claude Opus 5.5 just one‑shot,” which explains how to optimize CUDA kernels using a music‑video format. The clip was posted on September 27, 2026 and has accumu
Reasoning from scratch, round number 5! This time, talking about log-probability scoring (also a great fundamental concept for loss functions like cross-entropy in pre-training and distillation) and s
arXiv:2609.28476v1 Announce Type: cross Abstract: While a number of methods exist for counting pedestrians in street-view imagery, these mostly ignore the social dimensions of pedestrian activity. A s
musa: fix PH1 (MTT S5000) operator failures and build issues (#29193) musa: use 16-byte copies for MUSA like sm_70+ ggml_cuda_get_max_cpy_bytes() derives the copy width from CUDA_ARCH. mcc never defin
arXiv:2609.29519v1 Announce Type: new Abstract: Mental health disorders affect hundreds of millions of people around the world, yet access to professional counseling remains severely limited. AI-power
arXiv:2609.28758v1 Announce Type: cross Abstract: We describe our submission to the Unsupervised Speech in the Wild (UPS) Challenge at Interspeech 2026, a bidirectional Mamba-2 (BiMamba2) encoder trai
arXiv:2609.29525v1 Announce Type: new Abstract: A representation-adaptive kernel class produces, on a fixed sample, a union of reproducing-kernel Hilbert-space ellipsoids rather than one ellipsoid. We
arXiv:2508.07520v2 Announce Type: replace-cross Abstract: What makes a conversation hold together when its participants speak across one another? Topic maps offer one view, but they leave the relation
arXiv:2609.29075v1 Announce Type: new Abstract: Cancer registrars, including Oncology Data Specialists (ODSs), must interpret complex and frequently updated coding and staging standards. We developed
arXiv:2609.29256v1 Announce Type: cross Abstract: Glaucoma is the leading cause of irreversible blindness, and timely identification of fast progressors is essential to prevent disability. Current pra
arXiv:2609.29366v1 Announce Type: new Abstract: Multi-agent large language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewe
arXiv:2609.29545v1 Announce Type: new Abstract: Deployed agents run on handed-over knowledge: a frozen policy consults a briefing of consolidated items written before the stream begins. The world then
arXiv:2609.28749v1 Announce Type: new Abstract: Diffusion models have shown strong potential for kilometer-scale precipitation downscaling, but their performance in geographically unseen regions and e
arXiv:2609.29447v1 Announce Type: cross Abstract: Smart maritime infrastructures provide continuous access to heterogeneous sensing streams, enabling repeated experimentation, digital-twin development
arXiv:2609.29328v1 Announce Type: new Abstract: Understanding how Large Language Models (LLMs) encode linguistic structures remains a fundamental challenge in interpretability research. While diagnost
arXiv:2609.29398v1 Announce Type: new Abstract: Multimodal attributed graphs connect entities, visual content, language, and observed relations. Learning one foundation across such graphs requires mor
arXiv:2609.28587v1 Announce Type: cross Abstract: Large language models can interpret natural lan- guage, yet robust decisions remain challenging. Jev-like models expose structured choices, but these
arXiv:2609.29157v1 Announce Type: new Abstract: To achieve general-purpose autonomy over long horizons, a robot needs to maintain spatial environment information that supports a variety of tasks: geom
arXiv:2609.28775v1 Announce Type: cross Abstract: Ultrasound imaging increasingly targets portable, point-of-care, and wearable settings where constraints on power, bandwidth, and hardware complexity
arXiv:2609.30192v1 Announce Type: new Abstract: Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises f
arXiv:2512.14277v2 Announce Type: replace-cross Abstract: The advent of large language models is contributing to the emergence of novel approaches that promise to better tackle the challenge of genera
arXiv:2506.20584v3 Announce Type: replace Abstract: The most popular graph indices for vector search use principles from computational geometry to build the graph. Hence, their formal graph navigabili
Been dealing with the same thing a lot of people here probably are - RAM prices keep climbing and buying a single machine with enough memory for the models I actually want to run just isn't realistic
arXiv:2609.28506v1 Announce Type: new Abstract: TW3Cast is a time-series forecasting system that reaches position 3 of 130 entries on the GIFT-Eval benchmark by mean MASE rank, as of 2026-09-14. The t
arXiv:2609.28335v1 Announce Type: new Abstract: Claims about AI safety reach audiences well beyond the AI community, yet many rely on opaque evidence or static assessments, when supporting evidence is
metal : optimize sparse FA + clean-up (#29377) metal : cache sparse FA indices in shared memory Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp metal : simplify shared memory size calculation A