Knowledge catalogue
arXiv:2610.04093v1 Announce Type: new Abstract: Deep neural networks continue to grow in parameter count, driving up training and inference cost on GPUs. Sparse neural networks and Dynamic Sparse Trai
arXiv:2610.04999v1 Announce Type: new Abstract: The theoretical understanding of multi-layer neural networks is largely confined to overparameterized settings, which obscure parameter identifiability
arXiv:2610.04381v1 Announce Type: new Abstract: Fine-grained image editing requires more than producing a visually plausible result: an editor must execute the requested attribute change precisely whi
arXiv:2610.05921v1 Announce Type: cross Abstract: In generative models, Optimal Transport (OT) is used to improve Flow Matching (FM) by reducing noise-data coupling cost. However, different noise-to-o
arXiv:2610.05293v1 Announce Type: new Abstract: We describe the BossouChimpanzee video dataset, a unique long-term visual record of wild chimpanzees at an outdoor laboratory for field experiments in B
arXiv:2610.06571v1 Announce Type: new Abstract: Brain MRI interpretation is a longitudinal clinical reasoning problem: radiologists compare serial studies, integrate information across MRI sequences,
arXiv:2610.06725v1 Announce Type: new Abstract: Mixture-of-experts (MoE) layers increase model capacity without a proportional increase in per-example computation. However, conventional flat routers c
arXiv:2610.05400v1 Announce Type: cross Abstract: Long-video agents can actively gather question-relevant evidence, but they typically leave a central decision implicit: when has the agent seen enough
arXiv:2610.05618v1 Announce Type: cross Abstract: Finding which variables cause which others in multivariate time series, and at what lags, is central to science and policy, yet existing methods force
arXiv:2610.05863v1 Announce Type: new Abstract: High-quality child care in early life is a critical determinant of children's growth and development. Research on child care quality has been constraine
arXiv:2610.06238v1 Announce Type: new Abstract: We investigate the use of formal methods to provide tight and sound generalization bounds for learning algorithms. By casting the traditional notion of
arXiv:2610.05870v1 Announce Type: new Abstract: Generative models can synthesize high-quality inauthentic multimedia content that is already being misused at scale. We evaluate twenty deepfake detecto
arXiv:2610.05078v1 Announce Type: new Abstract: Accurate retinal vessel segmentation requires features that capture vascular geometry while preserving information for fine-scale reconstruction. We pro
arXiv:2406.12150v2 Announce Type: replace Abstract: Post-hoc attribution is widely used to identify important model inputs, but evaluating whether these attributions identify truly informative feature
arXiv:2610.05744v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) has been widely adopted in recent large language model (LLM) architectures. However, scaling up MoE in LLM training introduces
Claude Opus 5.5 leads at 63.31 and 4.99 per task. GPT 6 Astra is second at 56.25 and 11.61. Sonnet 5.5 follows at 53.14 and 2.82. At the other end, DeepSeek V4.1 Flash scores 36.91 at 0.26 and Ling 3.
arXiv:2610.04204v1 Announce Type: new Abstract: Training large language models (LLMs) entails a fundamental trade-off: memory-efficient optimizers such as Adam discard cross-parameter curvature, where
arXiv:2610.06829v1 Announce Type: cross Abstract: Open-source web agents are now strong enough to execute realistic browser tasks, but training them with reinforcement learning still depends on weak s
arXiv:2610.04558v1 Announce Type: cross Abstract: We present ClimateBench v2, a standardized protocol for evaluating climate models on diagnostics expected to be informative for their skill in project
Standard distillation usually means burning weeks of compute and billions of tokens hoping the student model eventually mimics the teacher. We wanted to see what happens if you skip backprop entirely
arXiv:2610.06679v1 Announce Type: new Abstract: Tabular foundation models perform in-context learning (ICL) by conditioning predictions on labeled training examples provided as context. Unlike traditi
arXiv:2610.05033v1 Announce Type: new Abstract: Generating a high-quality gaming world from a natural-language game intent requires joint reasoning about scene structure, spatial layout, gameplay obje
arXiv:2610.05481v1 Announce Type: cross Abstract: Large language models for code generation often fail on execution, multilingual coverage, and contamination control, especially under frozen backbone
arXiv:2610.05053v1 Announce Type: new Abstract: Domain Generalization (DG) for medical image segmentation is both highly challenging and critically important. However, existing medical DG methods larg
arXiv:2610.05913v1 Announce Type: new Abstract: Task-fMRI connectomes reveal state-dependent neural reconfigurations, yet conventional methods marginalize these signals by aggregating distinct conditi
arXiv:2610.05590v1 Announce Type: new Abstract: Cold-start drug-drug interaction (DDI) prediction tests whether models can identify clinically significant interactions for drugs without training-time
arXiv:2610.05127v1 Announce Type: new Abstract: Physics-informed neural network (PINN) training minimizes a weighted combination of partial differential equation (PDE), boundary-condition, and initial
arXiv:2610.06244v1 Announce Type: new Abstract: Planar graphs are central to applications across science and engineering, yet existing generators provide limited support for goal-directed generation u
arXiv:2510.06842v2 Announce Type: replace Abstract: Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation.
arXiv:2610.06171v1 Announce Type: new Abstract: Evaluating end-to-end autonomous driving under rare, safety-critical vehicle-pedestrian interactions requires photorealistic, sensor-level scenarios. Ho
arXiv:2610.05771v1 Announce Type: new Abstract: Lane and road markings provide critical guidance for vehicle navigation and multi-agent coordination, yet authoring them at scale remains a manual workf
arXiv:2610.06366v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed for automated software vulnerability analysis. Binary classification alone is insufficient; pra
arXiv:2610.04427v1 Announce Type: new Abstract: Neural operators offer an efficient alternative to classical PDE solvers, but most learn a monolithic map per equation family and discretization. Real s
arXiv:2610.03928v1 Announce Type: new Abstract: Screen localization and pointing estimation are key to low-cost interactive devices. Yet developing and evaluating these algorithms requires realistic d
On October 6 2026, Georgi Gerganov ( @ggerganov ) announced **day‑0 support for EmbeddingGemma 2 in llama.cpp** on Hugging Face. The announcement linked to the GGUF‑formatted model weights hosted unde
decision models + local ai = ❤️ tried Laya (421M) on llama.cpp in a little apple-picking benchmark, it's almost as good as Qwen 4B at 12x the speed. Media Decision models in llama.cpp are now availabl
arXiv:2610.03739v1 Announce Type: cross Abstract: The SWOT (Surface Water Ocean Topography) mission is currently providing unpreceded high-resolution measurements of Sea Surface Height (SSH), revealin
arXiv:2506.04619v2 Announce Type: replace Abstract: Image matching, which establishes correspondences between two images to recover 3D structure and camera geometry, is a cornerstone of computer visio
arXiv:2610.05531v1 Announce Type: new Abstract: Embodied systems need geometric perception that exploits available observations beyond images alone. Recent feed-forward 3D models incorporate geometric
Maybe I'm mistaken, but wasn't one of the big pros of Ollama Cloud inference that it was all hosted by Ollama? If that's the case, why duplicate the Deepseek on-/off- hour premiums? Surely they do not
arXiv:2412.10510v5 Announce Type: replace Abstract: The proliferation of disinformation demands reliable and scalable fact-checking solutions. We present Dynamic Evidence-based FAct-checking with Mult
arXiv:2610.05532v1 Announce Type: cross Abstract: AI agents that send emails, edit files, and make purchases must decide when to act on their own and when to check with the user first. This decision i
arXiv:2610.03945v1 Announce Type: new Abstract: A constrained optimization problem may involve a parameter in its objective and active constraints, yet the final decision may remain insensitive to sma
arXiv:2610.04392v1 Announce Type: new Abstract: Existing Anomaly Detection benchmarks are saturated and often unrealistic. As part of the VAND 4.0 Challenge, we introduce a hidden-test, application-dr
arXiv:2610.06834v1 Announce Type: cross Abstract: Some diffusion posterior samplers construct Gaussian-tilted intermediate distributions along the reverse process. We observe that these targets can be
arXiv:2610.05572v1 Announce Type: new Abstract: Predicting whether an LLM agent will fail has emerged as a promising direction for supporting intervention during execution. Recent approaches report st
arXiv:2610.04792v1 Announce Type: cross Abstract: Missing modality remains a longstanding challenge in multimodal learning. Existing methods typically address this issue through modality recovery or a
arXiv:2610.06204v1 Announce Type: cross Abstract: LLM agents are starting to own the full customer experience. Soon, LLMs may be selling and buying on behalf of companies and customers respectively. S
arXiv:2610.04636v1 Announce Type: cross Abstract: Increasing architectural complexity is often assumed to improve health misinformation detection, yet reported gains are difficult to interpret when st
arXiv:2610.05541v1 Announce Type: new Abstract: Mechanistic interpretability has emerged as the primary means to understand safety behavior of LLMs. However, existing tools primarily focus on the acti
arXiv:2610.04540v1 Announce Type: new Abstract: We introduce DreamFormer, a model-based agent that acquires language-conditioned, multi-task skills by imitating expert demonstrations within the latent
arXiv:2610.04489v1 Announce Type: cross Abstract: Understanding parameter functions helps elucidate the internal mechanisms of large language models (LLMs). However, how to connect parameters from dif
arXiv:2610.04137v1 Announce Type: new Abstract: Agent harnesses specify the roles, instructions, tools, and communication structure used to solve a task, and the right harness depends on the query. Be
arXiv:2610.05796v1 Announce Type: new Abstract: Optimisation-based parking planners usually impose collision constraints only at the time samples, so a vehicle corner can cut an obstacle between sampl
arXiv:2610.03736v1 Announce Type: cross Abstract: Probabilistic downscaling must represent kilometer-scale structure left unresolved by a deterministic regional prediction. We introduce an analog-init
arXiv:2610.06420v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative training of models across institutions without centralizing sensitive data, making it well-suited for priv
arXiv:2610.06147v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong zero-shot transferability but remain vulnerable to target-domain shifts at inference time. Test-time adapta
arXiv:2511.19935v3 Announce Type: replace Abstract: Deploying domain-specialized large language models on resource-constrained hardware motivates reducing both adaptation cost and the number of retain
arXiv:2610.04506v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly evaluated for egocentric and cross-view video reasoning, yet existing benchmarks largely focus on semanti
My comment on EmbeddingGemma 2 — Hacker News.I really appreciate that EmbeddingGemma 2 is under the Apache 2.0 license. For embedding models in particular, I don't think it makes sense to use a closed