Knowledge catalogue
arXiv:2608.26549v1 Announce Type: cross Abstract: While Physics-Informed Neural Networks (PINNs) have emerged as a transformative paradigm for solving complex differential equations, their reliance on
arXiv:2608.26113v1 Announce Type: new Abstract: We present PICasso, an AI-assisted framework for automated synthesis, verification, and optimization of photonic integrated circuits (PICs) from natural
arXiv:2608.26530v1 Announce Type: new Abstract: Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience
arXiv:2504.12588v4 Announce Type: replace-cross Abstract: Transformers have attained outstanding performance across various modalities, owing to their simple but powerful scaled-dot-product (SDP) atte
arXiv:2608.27151v1 Announce Type: new Abstract: Stable support remains challenging in robotic disassembly of irregularly shaped products. As components are progressively removed, the available support
arXiv:2608.26887v1 Announce Type: new Abstract: LLMs are thought to track 'belief states,' i.e., running probability distributions over the latent variables that govern language (Shai et al., 2024; Sa
arXiv:2608.26882v1 Announce Type: cross Abstract: Industrial control systems (ICSs) rely on programmable logic controllers (PLCs) to connect networked computation with physical control. Tool-using lar
arXiv:2503.13036v3 Announce Type: replace Abstract: Tactile skins based on electrical impedance tomography (EIT) enable large-area contact localization with few electrodes, but suffer from nonuniform
arXiv:2608.26142v1 Announce Type: cross Abstract: Referring Expression Segmentation (RES) aims to generate pixel-wise segmentation masks from complex and implicit textual queries. While recent advance
arXiv:2608.26700v1 Announce Type: new Abstract: Reply assistance in multilingual settings requires linguistic competence and culturally situated judgments of appropriateness. We present PragAlign, whi
arXiv:2608.26190v1 Announce Type: new Abstract: World models enable agents to reason about future outcomes and learn policies from their knowledge of state transition, but existing approaches primaril
arXiv:2608.26538v1 Announce Type: new Abstract: High-throughput drug screening relies on low-cost primary assays to prioritize compounds for more expensive dose-response profiling, where potency is ul
arXiv:2608.27165v1 Announce Type: new Abstract: Autoregressive large language models (LLMs) routinely generate factually incorrect outputs with high decoding confidence, limiting their deployment in h
arXiv:2608.26673v1 Announce Type: new Abstract: Large pretrained vision-language-action models dominate modern robot-manipulation benchmarks, but it remains unclear how much model scale is necessary f
arXiv:2608.26735v1 Announce Type: new Abstract: Specializing large language models to vertical domains improves domain-specific behavior but often degrades general capabilities such as reasoning, codi
arXiv:2608.26324v1 Announce Type: new Abstract: Best-of-N (BoN) sampling is the simplest and most widely deployed inference-time alignment strategy, but it suffers from two distinct problems: reward h
arXiv:2602.06110v2 Announce Type: replace Abstract: Publicly available clinical machine learning models pose an underappreciated privacy risk: their parameters or outputs can be exploited to recover i
arXiv:2608.27101v1 Announce Type: new Abstract: Ontology learning from text remains challenging despite significant progress in Large Language Models (LLMs), which can hallucinate domain terms, produc
arXiv:2608.26238v1 Announce Type: new Abstract: Native 3D generators now recover impressive mesh geometry from a single image. However, a dense mesh stays soft where a machined object should be sharp,
arXiv:2608.27205v1 Announce Type: new Abstract: Nitrogen rates for winter wheat are set before the season, under unknown prices and weather. The standard UK advice does not respond to prices, yet rece
arXiv:2608.26221v1 Announce Type: cross Abstract: As generative AI gains traction, researchers are investigating its potential to serve as proxies for humans. From undergoing cognitive psychology expe
arXiv:2608.26334v1 Announce Type: new Abstract: Automated theorem proving offers a natural foundation for recursive self-improvement in scientific discovery. However, existing neural provers do not fu
arXiv:2608.27392v1 Announce Type: cross Abstract: Camera-derived remote photoplethysmography (rPPG) is commonly validated through endpoint accuracy, but endpoint performance does not establish whether
arXiv:2508.05600v3 Announce Type: replace Abstract: Backdoor poisoning attacks are a threat to machine learning models that are trained on data collected from untrusted sources; these attacks enable a
arXiv:2608.26233v1 Announce Type: new Abstract: Extreme compression of deep neural networks, up to full binarization, dramatically reduces memory footprint and arithmetic complexity, facilitating depl
arXiv:2608.27370v1 Announce Type: new Abstract: Language model pretraining has become almost synonymous with prohibitive cost, placing it out of reach for much of the academic and open-source communit
arXiv:2508.06753v3 Announce Type: replace Abstract: The advent of ultra-low-bit LLM models, approaching the perplexity and task accuracy of their full precision counterparts, is ushering in a new era
arXiv:2601.05063v2 Announce Type: replace-cross Abstract: Magnetic resonance imaging (MRI) is a cornerstone of clinical neuroimaging, yet conventional MRIs provide qualitative information heavily depe
arXiv:2608.27302v1 Announce Type: new Abstract: Accurate identification of the correct view or angle in cardiac ultrasound (echocardiogram) is a critical component of cardiologic imaging. This step is
I wanted to see whether NInfer could run Qwen3.8-27B on an RTX PRO 4000 Blackwell 24GB. Hardware/software: NVIDIA RTX PRO 4000 Blackwell, 24GB 145W power limit CUDA 13.3 NVIDIA driver 610.x Ubuntu LXC
EDIT: Though the issue with q8 kv cache seems to arise from when and how often we run the quantize step, not that kv quantizing can't ever work - see comments for various proposed solutions --- One of
TL;DR: llama.cpp with --load-mode mmap used 21-32 GB of RAM, with ik_llama.cpp using 106-108 GB. -sm tensor killed my prefill, changing to -sm layer went from 36 tps to 135 tps. After that, -ubatch 20
I've got Qwen3.8-Flash-next running on RTX 3090, Ryzen 9 3950X, a PCIe 3.0 motherboard, and 64GB DDR RAM from 2020. IQ4_XS weights, full kvarn5 context, vision on GPU, experts in host RAM, n-grams on
arXiv:2608.27328v1 Announce Type: new Abstract: High similarity between first-visit and return frames does not necessarily show that a video world model remembered the scene; the intervening rollout m
arXiv:2608.26800v1 Announce Type: new Abstract: We present an online learning framework that enables a bimanual robot to acquire diverse juggling patterns directly on physical hardware within minutes,
arXiv:2608.27394v1 Announce Type: new Abstract: Retrieved scientific literature can serve as inspiration for both human and AI scientists. Inspiration can take different forms: prior work may directly
arXiv:2608.27358v1 Announce Type: cross Abstract: Influential public discourse shapes public beliefs and can also mislead, not only through what is stated, but also through how information is framed,
arXiv:2608.26644v1 Announce Type: new Abstract: Event cameras capture pixel-level intensity changes with microsecond resolution to produce highly sparse asynchronous data streams. For visual perceptio
arXiv:2608.26216v1 Announce Type: cross Abstract: The deployment of advanced, AI-enabled control algorithms in tokamak experiments requires robust integration with existing plasma control system (PCS)
arXiv:2608.26684v1 Announce Type: new Abstract: Recent large language models achieve strong performance on complex reasoning tasks, where reinforcement learning with Group Relative Policy Optimization
arXiv:2608.27036v1 Announce Type: new Abstract: Large Language Models (LLMs) can be trained to perform chain-of-thoughts reasoning in order to improve the reliability of their responses. In this work,
arXiv:2608.26671v1 Announce Type: new Abstract: Long autoregressive video generation faces a fundamental memory challenge: with a finite attention window, a model must decide which information from an
arXiv:2608.26120v1 Announce Type: new Abstract: Large Language Models (LLMs) are probabilistic models, typically defined by an autoregressive factorization. While recent work has begun to study richer
arXiv:2608.27407v1 Announce Type: new Abstract: Estimation of Human-Object Interactions in 3D (3D HOI) is a fundamental problem in 3D computer vision with applications in AR/VR, robotics, and embodied
arXiv:2608.27291v1 Announce Type: cross Abstract: Music recommendation relies primarily on two signals: user-item interactions, which fail in the cold-start regime, and intrinsic musical content, avai
arXiv:2402.09900v4 Announce Type: replace-cross Abstract: Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by map
arXiv:2608.27439v1 Announce Type: cross Abstract: LLM-based agents are increasingly deployed in product-level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state ch
arXiv:2608.26418v1 Announce Type: cross Abstract: Modern AI workloads and the hardware that runs them evolve on different timescales: architectural definition precedes volume silicon by years, while t
arXiv:2506.21599v5 Announce Type: replace-cross Abstract: Advancing large language models (LLMs) for the next point-of-interest (POI) recommendation task faces two fundamental challenges: (i) although
arXiv:2603.21695v2 Announce Type: replace Abstract: Novel view synthesis (NVS) through non-planar refractive surfaces presents fundamental challenges due to severe, spatially varying optical distortio
arXiv:2608.26167v1 Announce Type: new Abstract: Hallucination and abstention benchmarks rarely establish that a model could not have known the correct answer, making it difficult to distinguish approp
arXiv:2608.26860v1 Announce Type: cross Abstract: Connected and automated vehicle (CAV) platooning offers a promising approach to improving road safety and traffic capacity. However, platoon control i
arXiv:2509.00280v2 Announce Type: replace Abstract: Tensor decomposition (TD) is essential for analyzing high-dimensional sparse data, yet its irregular computations and memory-access patterns pose ma
arXiv:2608.26694v1 Announce Type: new Abstract: Detecting AI-generated text (AIGT) remains challenging because existing approaches rely on token-level statistical signals or independent stylometric fe
arXiv:2608.26622v1 Announce Type: new Abstract: Achieving stable, sustained grasping with soft robotic hands remains a fundamental challenge. Compliance enables safe and adaptive contact, yet the intr
We're releasing Qwen3.8-27B quantized with our newest methods, GSQ + RCO. Higher-quality models, same file size, now with the search and the quantizer both learned. What's inside: GSQ (Gumbel-Softmax
arXiv:2608.27020v1 Announce Type: cross Abstract: Hidden coordinates are not uniquely determined by a language model's input--output function, so representation-derived measurements should be invarian
arXiv:2608.27035v1 Announce Type: new Abstract: Korean constituency parsing raises a representational challenge because the terminal units of a phrase-structure tree do not straightforwardly correspon
arXiv:2608.27049v1 Announce Type: new Abstract: Reliable assessment of causal research designs in the social sciences is critical for evidence-based policy-making, yet has so far relied entirely on ma
arXiv:2608.26739v1 Announce Type: new Abstract: Accurate trajectory tracking in cable-driven lower-limb rehabilitation robots is challenging because model uncertainty, external disturbances, joint con