Knowledge catalogue
Obligatory plug for static embeddings. Are you using static embeddings in your projects? Would love to hear how people are leveraging them, whether for retrieval and beyond. Static embeddings offer un
arXiv:2608.27044v1 Announce Type: new Abstract: Multimodal representation learning has been shifting from traditional two-tower architectures to large language model (LLM)-based embedders due to their
arXiv:2608.26292v1 Announce Type: cross Abstract: Every memory-based knowledge editor in the SERAC lineage depends on a scope decision: given a query, does a stored edit apply? We report that current
arXiv:2608.26797v1 Announce Type: new Abstract: The rapid improvement of LLMs has made distinguishing AI-generated text from human writing a pressing problem. This challenge is further amplified by pa
arXiv:2608.26789v1 Announce Type: new Abstract: Accurate steering sensing and LiDAR-to-vehicle extrinsics are crucial for reliable path tracking in warehouse mobile robots (WMRs); miscalibration often
Proof is in the method honestly. Closed model labs need to constantly reinvent the wheel to keep lead. Open source has a bunch of independent labs practically working somewhat together. Eventually whe
OpenAI's own research says 80% of US GDP could be automated by agents today. So why isn't it? @swyx joined me on Navigators to break down what's actually holding back the adoption of agents (and it's
Ora runs agents on live websites and traces every step. When a signup, integration, or payment stalls, teams see which step, what the agent tried, and what to change. The whole platform is built on Ve
arXiv:2608.26866v1 Announce Type: new Abstract: Many multimodal tasks depend on how visual elements are ordered and composed, not only on recognizing them in isolation. Internet memes are a compact ca
A few days ago I posted asking what people considered the best local model for an 8 GB VRAM GPU. At the time, my personal sweet spot was Qwen3.6-35B-A3B, for agentic coding with Pi.dev. Well… Thanks t
arXiv:2601.20650v3 Announce Type: replace Abstract: Vast-horizon, repetitive workflows are common in daily routines, e.g., processing expense reports from a stack of receipts, organising a collection
Patrick Skinner tweets that the U.S. government is “broken” and urges citizens to reject and denounce what he calls “garbage” and its supporters. He emphasizes collective action as necessary to avoid
arXiv:2608.27137v1 Announce Type: cross Abstract: The recently envisioned goal-oriented communications paradigm requires machine learning inference to be performed directly on wirelessly transferred d
arXiv:2608.27206v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) demonstrate exceptional visual reasoning capabilities, yet their inference costs escalate rapidly with the proliferation
arXiv:2608.26180v1 Announce Type: cross Abstract: Shopping assistants are shifting from ranked product lists toward structured decision support, where systems must synthesize shopper context, product
arXiv:2608.26962v1 Announce Type: new Abstract: Molecular crystal structure prediction (CSP) is important in pharmaceuticals, agrochemicals, and organic electronics, where subtle differences in molecu
arXiv:2608.26658v1 Announce Type: cross Abstract: Generative retrieval has demonstrated strong performance by directly generating product semantic identifiers (SIDs). Extending this paradigm to image
arXiv:2608.27343v1 Announce Type: new Abstract: This paper addresses the recovery of essay-scale republication and reuse from fragmented text-reuse evidence, a setting whose central challenge is pair-
arXiv:2608.26720v1 Announce Type: new Abstract: Robotic and edge intelligence systems operate in dynamic environments where data arrives continuously, requiring models to adapt while preserving previo
arXiv:2608.27178v1 Announce Type: new Abstract: Accurate rectal cancer segmentation from magnetic resonance imaging (MRI) is essential for adaptive radiotherapy and tumor response assessment, but depl
arXiv:2608.27085v1 Announce Type: new Abstract: We study the problem of decentralized, self-organized task sharing for a swarm of heterogeneous robots that collaborate in transportation or other objec
arXiv:2608.27345v1 Announce Type: cross Abstract: Recent video generation models are increasingly framed as world models. Many physical processes can unfold in more than one valid way. Therefore, a wo
PDF parsing is fun because there's an infinite variety of enteprise documents 📑. For each document category, there's a long tail of work to build more precise bounding boxes, confidence scores, and do
arXiv:2608.26951v1 Announce Type: cross Abstract: Feed-forward 3D Gaussian Splatting reconstructs an explicit Gaussian representation from multiple input images in one network execution, making 3D rec
arXiv:2608.27046v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) and other RL-style post-training paradigms have been used for aligning large language models (LL
arXiv:2608.27427v1 Announce Type: cross Abstract: Large language model (LLM) agents in governed organizations must let the persona (instructions, tone, self-presentation) evolve freely, while keeping
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