Knowledge catalogue
arXiv:2609.27032v1 Announce Type: new Abstract: Faithfulness is a central concern in legal text summarization, which motivates extractive approaches that select verbatim content traceable to its sourc
arXiv:2609.28327v1 Announce Type: new Abstract: We present LightMIS, a scalable family of ultra-lightweight convolutional networks for 2D binary medical image segmentation without a learned stage-wise
arXiv:2609.27741v1 Announce Type: new Abstract: In value-based reinforcement learning, improving the accuracy of policy evaluation has been shown to improve downstream policy optimization performance.
arXiv:2609.27303v1 Announce Type: new Abstract: Livestreams are long-lasting interactive environments where audiovisual content, viewer activity, host behavior, and platform signals evolve together, c
arXiv:2609.27092v1 Announce Type: cross Abstract: Many node-classification GNNs apply a linear classifier to a nonnegative mixture of local messages. An error can reflect either poor mixture weights o
arXiv:2608.24707v2 Announce Type: replace Abstract: While text-based hallucination detection is well studied, reference-free detection of factual alterations in speech remains underexplored, especiall
I'm about to buy a Mac Studio mainly for running LLMs locally and I'm stuck between two configs: M5 Ultra (30/64) with 96GB: 1.2 TB/s bandwidth, roughly 1.7x faster generation and much faster prefill
arXiv:2609.27041v1 Announce Type: new Abstract: Mathematical reasoning benchmarks are typically organized by topic, but language models may organize their internal computation by reusable reasoning ap
arXiv:2609.28399v1 Announce Type: new Abstract: Language models typically construct attention values from contextual hidden states, even when some of their content may be reusable across contexts. We
arXiv:2603.16868v2 Announce Type: replace-cross Abstract: Monocular 3D scene reconstruction has recently seen significant progress. Powered by the modern neural architectures and large-scale data, rec
arXiv:2609.27142v1 Announce Type: new Abstract: Text-to-image retrieval with frozen dual encoders degrades when the query names a small, visually subordinate object in a cluttered scene: a single glob
arXiv:2609.28438v1 Announce Type: new Abstract: We study minimal-norm interpolation and ell_2-regularized logistic-loss minimization for binary classification by univariate two-layer ReLU networks. We
arXiv:2609.28344v1 Announce Type: cross Abstract: Audio-language models (ALMs) integrate acoustic perception with the knowledge encoded in language models, enabling contextual understanding of auditor
MLPerf Training v6.1 adds an agentic reinforcement-learning workload that measures how quickly systems can teach a 397-billion-parameter language model to repair real software projects. The post MLPer
Model Overview Ling-3.0-flash-VL inherits the language, reasoning, and long-context capabilities of Ling-3.0-flash, while extending them with native image and video understanding. The model has 124B t
arXiv:2609.27349v1 Announce Type: new Abstract: Real-world molecular design remains challenging for large language model (LLM)-based agents. It requires them to interpret design contexts, satisfy mult
arXiv:2609.26872v1 Announce Type: new Abstract: Musculoskeletal (MSK) humanoids provide a physiologically grounded embodiment for studying full-body motor control, but their high-dimensional muscle ac
arXiv:2609.28437v1 Announce Type: new Abstract: Online information is increasingly consumed in video format. Much of this comes in the form of *raw video*: continuous footage taken on a cell phone, wi
arXiv:2609.27590v1 Announce Type: new Abstract: Long-context evaluations often test whether a model can recover distant evidence, but recoverability does not guarantee behavioral influence. We test th
These boards cost me 115 each and I have them connected using llama.cpp with Vulkan and RPC on Bazzite. The boards have roughly 27GB of combined GPU memory and communicate over 1gb Ethernet. For aroun
arXiv:2609.27086v1 Announce Type: new Abstract: NADI 2026 is the seventh edition of the Nuanced Arabic Dialect Identification (NADI) shared task series and the second dedicated to multidialectal Arabi
arXiv:2609.27372v1 Announce Type: cross Abstract: Benchmarks for full-duplex spoken dialogue models score turn-taking with binary fixed-window rules that reward immediate response or silence by comple
I'm in a position where I didn't mean to go down this AI rabbit hole... I was looking into mental cognitions and how the mind is made up and learned that my old RTX 5k could run small models. So that
arXiv:2609.27735v1 Announce Type: new Abstract: Newton-Schulz (NS) iteration has recently been used in the Muon optimizer to transform update matrices during the training of large language models. Mot
arXiv:2607.11433v2 Announce Type: replace Abstract: Omni-modal agents must seek evidence across video, audio, web pages, and computation to answer questions. Their main bottleneck is planning: noisy m
arXiv:2609.26918v1 Announce Type: cross Abstract: Hindsight relabeling which retroactively replacing a transition's goal with the outcome the agent actually achieved is an effective tool for improving
arXiv:2509.18088v2 Announce Type: replace-cross Abstract: Efficient resource allocation in multi-agent systems requires autonomous agents to coordinate their decisions while balancing system-wide obje
arXiv:2511.15375v2 Announce Type: replace-cross Abstract: Domain-specific post-training often causes catastrophic forgetting, making foundation models lose their general reasoning ability and limiting
arXiv:2609.28197v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents that alter real-world states, ensuring operational safety across multi-step workflows has
arXiv:2609.28286v1 Announce Type: new Abstract: Estimating the Planetary Boundary Layer Height (PBLH) from satellite observations is a challenging regression problem due to the indirect relationship b
arXiv:2609.27205v1 Announce Type: cross Abstract: Text-to-speech systems increasingly process user-generated text (UGT) such as ppl and imo, whose pronunciation must be inferred from the canonical rat
arXiv:2609.27288v1 Announce Type: new Abstract: The Abstraction and Reasoning Corpus (ARC) has become a prominent benchmark for evaluating general abstract reasoning and fluid intelligence in AI model
Following our announcement of Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking last week, we are thrilled to share that Gemini 3.8 Live with Live Avatar is now generally available in Gemini Enter
arXiv:2609.26890v1 Announce Type: new Abstract: Many physical data assimilation (DA) workflows require smoothing methods that represent non-Gaussian posteriors over physical state variables, scale to
arXiv:2607.19114v2 Announce Type: replace Abstract: Activities in aqueous electrolyte solutions, usually described by ionic activity and osmotic coefficients, are important properties for modeling man
arXiv:2609.27395v1 Announce Type: new Abstract: Compact vision-language models (VLMs) now power a growing share of multimodal applications. The benchmarks used to compare them, however, inherit a fron
arXiv:2609.27076v1 Announce Type: new Abstract: Open-vocabulary visual grounding enables robots to localise task-relevant entities from natural-language queries without dependence on predefined percep
Introduction The landscape of software supply chain security has undergone a significant shift. Recent campaigns demonstrate that sophisticated threat actors are systematically targeting the engineeri
arXiv:2609.28049v1 Announce Type: cross Abstract: Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evi
arXiv:2609.27105v1 Announce Type: new Abstract: Generalized planning aims to compute a plan that solves all instances of a planning domain. Recent work has used LLMs to automatically generate and debu
Just a quick PSA. llama.cpp does have prompt caching. if you are running large context lengths and have long multiturn projects, increasing -cram can provide you with massive speedups. There is a poin
arXiv:2609.27074v1 Announce Type: cross Abstract: This study introduces a dual-matrix computational architecture to mathematically quantify the morphological and theological divergence of 196 Hindu an
arXiv:2609.28391v1 Announce Type: cross Abstract: Score matching has driven major advances in classical generative learning by enabling models to learn from data without evaluating intractable normali
Many a praise have been sung on Qwen-3.8, but here is mine. Qwen-3.8 and I had a rocky start, because it thinks so much. Watching it working is painful, so you have to stop doing that. You have to let
Personal note first, being straight with you: I'm lazy tonight and used AI to write the following post: The workflow, the conversion work, and the mistakes that taught me the stuff below are mine, and
A while ago I posted 15 tok/s output and 100-120 tok/s prompt processing with the IQ3_XXS quant on a 12GB RTX 5070 using llama.cpp. Since then I built my own inference engine for this one model and th
I was actually pretty happy with my Qwen3.8-27b setup, and I'd been tinkering with Ninfer to have a version that was 'fast but maybe a bit stupid' and the speed was nice to have as a backup. But I was
Here's my *first* implementation of KVA projectors on QFN (just the uncensored model for now) the highlights are basically as follows for using the projectors at each different layer: Starting at laye
arXiv:2609.27855v1 Announce Type: new Abstract: AI systems increasingly claim to optimize prompts, policies, architectures, plans, tool-use trajectories, reasoning traces, and test-time computation. T
arXiv:2609.27173v1 Announce Type: new Abstract: Solving complex tasks in domains such as science, medicine, law, and finance often requires assembling interdependent information scattered across vast,
arXiv:2609.26942v1 Announce Type: cross Abstract: Current literature evaluates large language models (LLMs) on multilingual kinship understanding using multiple choice benchmarks, treating it as a rec
arXiv:2609.27986v1 Announce Type: new Abstract: Accurate remaining discharge time (RDT) prediction is challenging in real-world battery applications because future load profiles are unknown and highly
arXiv:2609.27248v1 Announce Type: new Abstract: Next-token prediction has enabled highly fluent autoregressive language models, but it represents global structure only indirectly through sequential fa
arXiv:2609.26979v1 Announce Type: new Abstract: Gaussian processes (GPs) provide a flexible framework for learning unknown functions from noisy measurements while quantifying predictive uncertainty, m
arXiv:2609.27982v1 Announce Type: cross Abstract: In this paper, we are concerned with matrices formed by block-diagonal factors interleaved with fixed permutations -- a flexible family of structured
arXiv:2609.27981v1 Announce Type: new Abstract: KV-cache eviction is typically evaluated through average quality-memory trade-offs, yet a small average loss can hide requests whose utility degrades ma
arXiv:2609.27677v1 Announce Type: new Abstract: Fixed roadside cameras repeatedly observe a stable scene overlaid by sparse moving traffic. Temporal memory can recover weak observations, but reusing m
Context: we build an open-source (MIT) self-hosted database client and added a natural-language-to-SQL assistant that can point at a local runtime like Ollama instead of a hosted API. I want to share
arXiv:2603.17373v2 Announce Type: replace Abstract: Large language models are rapidly being deployed as AI tutors, yet current evaluation paradigms assess problem-solving accuracy and generic safety i
arXiv:2609.27678v1 Announce Type: new Abstract: Contract inference requires multiple judgments about a shared document, but aggregate accuracy can conceal changes in the individual decisions. Repeated