Knowledge catalogue
arXiv:2604.18092v1 Announce Type: new Abstract: Small language models fine-tuned for graph property estimation have demonstrated strong in-distribution performance, yet their generalization capabiliti
arXiv:2604.18460v1 Announce Type: new Abstract: Multimodal affective computing aims to predict humans' sentiment, emotion, intention, and opinion using language, acoustic, and visual modalities. Howev
arXiv:2604.18482v1 Announce Type: cross Abstract: Safety filters have been shown to be effective tools to ensure the safety of control systems with unsafe nominal policies. To address scalability chal
arXiv:2604.17156v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) have emerged as a promising framework for solving inverse problems governed by partial differential equations (
arXiv:2604.14156v1 Announce Type: new Abstract: Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work ha
arXiv:2603.27844v2 Announce Type: replace Abstract: Majority voting over multiple LLM attempts improves mathematical reasoning, but correlated errors limit the effective sample size. A natural fix is
arXiv:2602.03295v2 Announce Type: replace Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated remarkable capabilities. However, their deployment is hindered by s
arXiv:2604.13252v1 Announce Type: new Abstract: Anomaly detection aims to identify observations that deviate from expected behavior. Because anomalous events are inherently sparse, most frameworks are
arXiv:2512.15742v2 Announce Type: replace Abstract: Pre-trained Vision Kolmogorov-Arnold Networks (KANs) store a dense B-spline grid on every edge, inflating prediction-head parameter counts by more t
arXiv:2601.10245v2 Announce Type: replace-cross Abstract: Multi-step reasoning tasks like mathematical problem solving are vulnerable to cascading failures, where a single incorrect step leads to comp
arXiv:2604.12913v1 Announce Type: cross Abstract: Binary decompilation is a critical reverse engineering task aimed at reconstructing high-level source code from stripped executables. Although Large L
Artificial intelligence infrastructure startup Parasail Inc. today announced that it has raised 32 million in early-stage funding. Touring Capital and Kindred Ventures jointly led the Series A round.
arXiv:2604.09752v1 Announce Type: cross Abstract: During the deployment of Large Language Models (LLMs), the autoregressive decoding phase on heterogeneous NPU platforms (e.g., Ascend 910B) faces seve
arXiv:2604.11410v1 Announce Type: new Abstract: We present a framework for bridging the gap between sensor attack detection and recovery in cyber-physical systems. The proposed framework models modern
arXiv:2604.09673v1 Announce Type: cross Abstract: The mirror self-recognition test evaluates whether a subject touches a mark on its own body that is visible only in a mirror, and is widely used as an
arXiv:2509.17458v3 Announce Type: replace-cross Abstract: Text-to-image diffusion models, such as Stable Diffusion, can produce high-quality and diverse images but often fail to achieve compositional
arXiv:2604.10030v1 Announce Type: new Abstract: Video diffusion models have achieved remarkable progress in generating high-quality videos. However, these models struggle to represent the temporal suc
arXiv:2604.09613v1 Announce Type: cross Abstract: Production vLLM fleets provision every instance for worst-case context length, wasting 4-8x concurrency on the 80-95% of requests that are short and s
arXiv:2604.04161v2 Announce Type: replace Abstract: In Vision-Language-Action (VLA) models, action chunking (i.e., executing a sequence of actions without intermediate replanning) is a key technique t
arXiv:2604.08863v1 Announce Type: new Abstract: Recovering analytical solutions of physical fields from visual observations is a fundamental yet underexplored capability for AI-assisted scientific rea
arXiv:2604.08648v1 Announce Type: cross Abstract: We motivate the use of differentiable probabilistic programming techniques in order to account for the large model-space inherent to astrophysical gam
arXiv:2604.08148v1 Announce Type: new Abstract: We propose a lightweight hybrid approach to clickbait detection that combines OpenAI semantic embeddings with six compact heuristic features capturing s
arXiv:2509.22750v3 Announce Type: replace Abstract: Real-world multi-hop QA is naturally linked with ambiguity, where a single query can trigger multiple reasoning paths that require independent resol
arXiv:2604.06217v1 Announce Type: cross Abstract: The foundation model era -- roughly 2020 to 2025 -- is over. The forces that defined it have inverted. Open source models have reached frontier perfor
Physical Intelligence (Pi) is building a general-purpose robotic intelligence system whose core Visual-Language-Action (VLA) model takes visual observations, natural-language instructions, and the...
Did a comparison of speed on Apple Silicon a few days ago. Here is the short recap, and then the full text: https://releases.drawthings.ai/p/harvest-season-new-hardware-new-inference Title poster is g
arXiv:2506.03371v2 Announce Type: replace Abstract: Recent advances in vision-language models (VLMs) have enabled accurate image-based geolocation, raising serious concerns about location privacy risk
arXiv:2610.12568v2 Announce Type: replace Abstract: Feed-forward 3D priors enable high-quality reconstruction from image streams but often lack reliable metric scale and suffer from long-term trajecto
arXiv:2603.23678v2 Announce Type: replace Abstract: Large Language Models (LLMs) offer transformative solutions across many domains, but healthcare integration is hindered by strict data privacy const
arXiv:2610.20292v1 Announce Type: new Abstract: Reliable medical reasoning requires LLMs to dynamically access external biomedical evidence to improve factual trustworthiness and reasoning accuracy. H
arXiv:2610.19814v1 Announce Type: new Abstract: Transformer-based tabular foundation models (TFMs) achieve state-of-the-art performance on small to medium-sized tabular prediction tasks while processi
arXiv:2610.15789v1 Announce Type: cross Abstract: In this paper, we develop an asymptotically normal estimator for the value of policy improvement (VPI) under adaptively collected data. This value, wh
[UPDATE / RETRACTION: The '100% GTO' claim had a prompt-leakage bug] We patched the repo to pass strictly neutral states, here are the real, honest numbers: • Latency: Still ~2ms (ONNX + Absorbing Mar
arXiv:2610.16793v1 Announce Type: new Abstract: Interacting with unfamiliar objects requires understanding how their parts connect and move. We introduce ViewStruct, a framework for jointly predicting
arXiv:2610.13605v1 Announce Type: new Abstract: Dynamic vocabularies built on-the-fly via Lempel-Ziv-Welch (LZW) compression let a language model represent the same text in fewer tokens, but prior wor
arXiv:2405.15662v2 Announce Type: replace Abstract: Machine unlearning aims to remove the influence of specified training data or knowledge from a trained model without requiring full retraining. This
I posted on here a while back asking for advice on upgrading to an Epyc system. Thanks to all who commented. I’ve taken the plunge and ordered: - Epyc 7443 CPU (24 cores, 48 threads, 128 lanes) - H12S
arXiv:2610.12212v1 Announce Type: new Abstract: Bayesian neural network predictions are commonly approximated using a fixed number of Monte Carlo samples per input, without controlling the resulting e
arXiv:2610.09956v1 Announce Type: cross Abstract: Probing the hypothesis space after seeing the data remains valid under possibilistic inferential models (IMs), provided the significance level stays f
arXiv:2610.08765v1 Announce Type: new Abstract: Control barrier functions (CBFs) certify commands through an assumed dynamics model, so an abrupt, unmeasured regime change can undermine the certificat
I’m hitting rate limits on Together AI. For context, I’ve been working on an agentic repository indexing and benchmark generation tool, and I’m running multiple agents in parallel across models like L
arXiv:2610.05058v1 Announce Type: cross Abstract: Pointwise Mutual Information (PMI) is a core measure of testing word association, and Skip-gram with Negative Sampling (SGNS) is essentially a method
I forked llama.cpp's server into AgrillaMoE, a dedicated build for Qwen3.6-35B-A3B (~A4B) with Unsloth quants. On a (vant.ai) rented V100 16GB with the 2-bit UD-Q2_K_XL quant it generates at ~57-60 to
arXiv:2610.00793v1 Announce Type: cross Abstract: We consider the estimation of drift, diffusion, and noise covariance from discrete observations of stochastic differential equations driven by Gaussia
arXiv:2610.01640v1 Announce Type: cross Abstract: Vision-language models (VLMs) face a fixed-budget trade-off between processing more visual information for fine-grained perception and using a larger
arXiv:2609.36967v1 Announce Type: new Abstract: Existing VLA pruning strategies primarily select individual visual tokens according to task-level semantic relevance, while overlooking the spatial info
arXiv:2609.36689v1 Announce Type: cross Abstract: Large language models have achieved significant progress in event forecasting, yet their probability outputs exhibit systematic calibration bias that
arXiv:2609.38006v1 Announce Type: new Abstract: Running a language model locally offers advantages in privacy, latency, and cost, but local hardware fits only small models, which are less capable than
arXiv:2609.31857v2 Announce Type: replace Abstract: Validating an LLM-as-a-judge requires estimating its agreement with humans, yet annotation budgets rarely allow every item to be multiply labeled. W
arXiv:2609.33748v1 Announce Type: new Abstract: World-action models (WAMs) couple predictive visual modeling with action generation, typically relying on iterative denoising with a fixed denoising ste
arXiv:2609.32486v1 Announce Type: new Abstract: Deploying a language model under different computing and latency budgets calls for compact models with different quality-cost trade-offs. Towards this e
arXiv:2609.33561v1 Announce Type: new Abstract: Multimodal graph predictors combine text, images, and relations to classify connected entities. How much of this input is needed to preserve their predi
arXiv:2609.32456v1 Announce Type: new Abstract: World modeling under partial observation requires reasoning about the complete worlds that remain compatible with limited visual evidence. Occluded obje
arXiv:2609.34043v1 Announce Type: cross Abstract: Non-negative matrix factorization (NMF) is a singular statistical model whose Bayesian asymptotics are governed by the real log canonical threshold (R
Here's the project. I have nothing to do with it. I'm just an amazed user. https://github.com/gufo-org/gufo/blob/main/docs/models/qwen3.8-flash-next/BENCHMARKS.md Those benchmark numbers hold up on re
arXiv:2609.30769v1 Announce Type: new Abstract: Cross-domain few-shot learning requires adapting a classifier to a new visual domain from very few labelled examples without target-time parameter updat
Hello everyone, I made a calculator for the theoretical HW roofline for decoding / prefill based on several parameters (LLM model architecture, quants, GPU, Memory, ..). It still a theoretical bound,
arXiv:2609.28551v1 Announce Type: cross Abstract: When can a learner make only finitely many prediction errors along every infinite sequence labeled by a fixed, unknown hypothesis? We characterize thi
arXiv:2609.29032v1 Announce Type: cross Abstract: Sparse activation reduces mixture-of-experts computation without eliminating the need to store all experts. We present Routide, a Swift/MLX runtime th
arXiv:2609.28563v1 Announce Type: new Abstract: Spatial transcriptomics (ST) profiles gene expression within tissue architecture, but its cost and experimental complexity limit routine use. Predicting