Knowledge catalogue
arXiv:2609.12653v1 Announce Type: new Abstract: Russian state propaganda spreads across many languages and online spaces. Yet, most computational work examines only one such space, usually social medi
This is an evolution on top of Raymond's KV cache streaming fork - all credits to what enabled this goes to him. The basic idea behind what he enabled was a pool of memory in VRAM that is used differe
arXiv:2609.11636v1 Announce Type: new Abstract: Domain practitioners understand their business constraints but may lack operations-research expertise or dedicated support. LLM-based optimization agent
arXiv:2609.11065v1 Announce Type: new Abstract: Graph Retrieval-Augmented Generation (GraphRAG) can connect evidence distributed across a corpus graph, but most systems use largely shared exploration
While browsing a benchmark list site, I spotted a recently published 33B parameter model which claimed to beat Qwen3.8 27b on the ArtificialAnalysis (AA) intelligence index. I was obviously excited. B
Planning to build a PC mainly for local LLMs/coding agents. I keep seeing 3090 + Qwen 3.8 Flash Next benchmarks, but could not find enough info for the 7900 XTX 24GB. 3090s are hard to find where I li
arXiv:2609.10654v1 Announce Type: cross Abstract: The Abstraction and Reasoning Corpus (ARC) benchmarks cognitive generalization, the ability to infer and apply abstract rules from limited examples. T
arXiv:2609.10564v1 Announce Type: cross Abstract: Recent machine learning weather prediction (MLWP) models have demonstrated remarkable forecasting skill on global reanalysis-based benchmarks. However
arXiv:2603.24125v3 Announce Type: replace Abstract: During training, Large Language Models (LLMs) learn social regularities that can lead to gender bias in downstream applications. Most mitigation eff
arXiv:2609.11246v1 Announce Type: new Abstract: Kurdish is spoken by millions of people, but little technology can read it aloud. A recent study released three Kurdish voices, 35 hours of recorded spe
arXiv:2609.11870v1 Announce Type: new Abstract: A language model normally begins training with random word embeddings: whatever 'banana' means must be learned from training corpora. I implement St. Au
Comparing models on dollars per million tokens misses what production workloads actually pay for: outcomes. This post shares an open-source benchmarking harness that measures cost per correct answer,
arXiv:2609.11172v1 Announce Type: new Abstract: Recent visual generators produce high-fidelity images yet often violate physical consistency under ego-motion, limiting their use for spatial reasoning
arXiv:2609.09229v1 Announce Type: cross Abstract: Additional inference compute can increase the number of correctly resolved security-assurance tasks, but repeated success, unique coverage, accepted e
arXiv:2609.10413v1 Announce Type: new Abstract: Current LLM memory systems treat all personal facts identically, so stores grow without bound while retrieval precision degrades. The core challenge is
arXiv:2609.11134v1 Announce Type: new Abstract: Most Deepfake detectors report near-perfect AUC scores on their reference benchmarks. However, a recent ICML position paper argues that these evaluation
arXiv:2609.11736v1 Announce Type: cross Abstract: We develop a quantum approach to spectral feature extraction from the density of states (DOS) of a problem-dependent Hamiltonian, and apply it to mach
arXiv:2603.15617v2 Announce Type: replace Abstract: Can AI make progress on important, unsolved mathematical problems? Large language models are now capable of sophisticated mathematical and scientifi
arXiv:2609.10550v1 Announce Type: cross Abstract: AI deployment performance is shaped not by model architecture alone, but by interactions among compression, compiler transformations, and serving poli
arXiv:2609.09664v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as personalized assistants that interact with users over extended periods of time. As conversatio
arXiv:2609.09657v1 Announce Type: new Abstract: Existing emotional support conversation systems mainly focus on one-on-one seeker-supporter interactions and individual emotional states, leaving interp
arXiv:2609.11864v1 Announce Type: cross Abstract: Speech large language models (SpeechLLMs) offer reduced latency and retain paralinguistic nuances that are typically lost in cascaded automatic speech
I’ve been building 'Spomin', a router that replaces context with summaries directly in the KV cache. The goal is to keep long running sessions going without repeatedly stopping for full compaction and
arXiv:2609.10824v1 Announce Type: cross Abstract: Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and construct reusable resources such as indices, s
Some people says terminal bench reflects model intelligence better than the intelligent index. From the look of it, the ranking does seem to reflect how people feel about the open and closed models. F
arXiv:2609.10357v1 Announce Type: new Abstract: Time-series foundation models are evaluated almost exclusively on public archives that predate them, so a strong score cannot be separated from having s
arXiv:2609.06914v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong capabilities across diverse domains, showing considerable potential in medicine. However, their ap
arXiv:2603.20957v4 Announce Type: replace-cross Abstract: Frontier LLM companies have repeatedly assured courts and regulators that their models do not store copies of training data. They further rely
arXiv:2609.08071v1 Announce Type: new Abstract: Firms making inventory decisions have access to operational data, optimization tools, and large language models (LLMs). Typically, data characterize the
arXiv:2609.10346v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) process hundreds or thousands of visual tokens per image, incurring prohibitive inference costs. While existing
arXiv:2609.08566v1 Announce Type: new Abstract: KV cache is evolving from a serving optimization into an external memory substrate for long-term LLM agents. In a shared multi-user deployment, however,
arXiv:2609.09510v1 Announce Type: cross Abstract: High-risk non-muscle-invasive bladder cancer (HR-NMIBC) carries substantial risks of recurrence and progression, while current clinical risk stratific
arXiv:2609.08832v1 Announce Type: new Abstract: Large language model (LLM)-powered agents can be accurate on average yet unreliable in production, a discrepancy that has been observed but remains larg
Title says it all. https://github.com/gjabdelnoor/Day1DeepseekV4.1-CPU The goal is pretty simple, I like having infinite slow tokens from the bioinformatics machine in the lab to run overnight or over
arXiv:2602.05354v3 Announce Type: replace Abstract: Autonomous web agents are increasingly deployed in moderation and policy enforcement, where correct decisions often depend on evidence that is not i
arXiv:2601.13591v3 Announce Type: replace Abstract: Recent LLM-based data agents aim to automate data science tasks ranging from data analysis to deep learning. However, the open-ended nature of real-
arXiv:2609.10335v1 Announce Type: cross Abstract: Plane geometry remains a significant challenge in AI, requiring the integration of visual perception and mathematical reasoning. While Large Multimoda
arXiv:2609.10293v1 Announce Type: new Abstract: In high-stakes domains such as legal practice, a language-model answer is only useful to the extent that a reader can verify each claim against the sour
I’ve been working on perfecting my setup ever since 3.8 hit, but no longer pay for subscriptions. I had a coding interview today and setup openrouter ahead of time as another option. I figured I could
arXiv:2609.08869v1 Announce Type: cross Abstract: Analysts in emerging equity markets keep answering the same questions. Did fundamentals match the market's response? How does the local currency co-mo
arXiv:2609.10055v1 Announce Type: cross Abstract: Biomedical ontology normalization maps free-text expressions to standardized concepts, enabling consistent integration and analysis of biomedical data
arXiv:2609.10540v1 Announce Type: new Abstract: Recent video world models generate increasingly realistic and interactive visual experiences, yet lack reliable mechanisms for maintaining persistent wo
arXiv:2609.10092v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate bec
arXiv:2609.05512v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) impose substantial energy costs during deployment, yet current compression methods apply uniform quantization across all c
arXiv:2609.07559v1 Announce Type: new Abstract: How do you validate a cheap, deterministic proxy for an oracle that is expensive, rate-limited, and non-stationary? We present a protocol built on adver
arXiv:2609.07344v1 Announce Type: cross Abstract: Large language model (LLM) based agents are increasingly applied to cybersecurity tasks such as vulnerability discovery and automated penetration test
arXiv:2609.09815v1 Announce Type: cross Abstract: Compound LLM systems often solve a coordination problem by adding a higher-level LLM. The resulting meta-agent reads workers' outputs, writes the fina
arXiv:2609.07065v1 Announce Type: new Abstract: Agent-to-agent (A2A) alpha discovery is slowed by repeated feedback cycles between mining and evaluation agents, whose hand-offs, in contemporary LLM mu
arXiv:2609.05531v1 Announce Type: cross Abstract: No specification says how a governed autotelic AI agent organization, where agents pursue self-generated goals inside guardrails, should be designed a
arXiv:2609.07741v1 Announce Type: new Abstract: Persistent AI assistants are intended to extend human attention, memory, and coordination across changing digital and physical environments. To be truly
arXiv:2609.06610v1 Announce Type: new Abstract: Professional box-lacrosse statistics summarize outcomes but provide limited information about shot quality or the roles behind scoring opportunities. Th
arXiv:2609.07884v1 Announce Type: new Abstract: Recent work, such as Vision Banana, shows that lightweight instruction tuning can enable an image generator to achieve state-of-the-art performance acro
arXiv:2609.07188v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection is critical for safe deployment of medical AI systems. Recently, test-time adaptation (TTA) has emerged as a new par
arXiv:2609.07981v1 Announce Type: cross Abstract: Audio provenance attribution - which system produced a synthetic utterance - is reported at near-ceiling accuracy on clean benchmarks, yet audio reach
arXiv:2609.06133v1 Announce Type: new Abstract: Sequential inference on small devices requires a model to retain useful history without repeatedly processing a long input record. A Recurrent Tsetlin M
arXiv:2609.08242v1 Announce Type: new Abstract: Vision-language models (VLMs) demonstrate strong performance across compositional reasoning benchmarks, which require reasoning over semantic perturbati
arXiv:2609.05539v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have recently made strong progress in vision-language reasoning, yet their performance often degrades as genera
arXiv:2609.08705v1 Announce Type: new Abstract: Table Structure Recognition (TSR) aims to extract the bounding boxes of cells and table structure (e.g., HTML) from table images. Although current appro
arXiv:2609.08896v1 Announce Type: cross Abstract: The rapid growth of multimodal data has intensified the need for question answering (QA) systems capable of reasoning across heterogeneous sources suc
arXiv:2609.06046v1 Announce Type: cross Abstract: We present a modular, high-fidelity simulation framework for the development and benchmarking of flight control strategies in fixed-wing aerial robots