Knowledge catalogue
arXiv:2609.09417v1 Announce Type: new Abstract: Vision-language models (VLMs) show promise for agricultural classification, but zero-shot performance on disease, pest, damage, quality, and species ide
Anyone else play with vllm-mlx? There was an interesting paper that came out that compared this version of vllm that was originally designed for multi modal inference performance gains, but ended up s
arXiv:2609.09985v1 Announce Type: new Abstract: Real-world video understanding requires integrating visual, audio, textual, and temporal evidence distributed across a video. Yet many pipelines use a f
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:2609.06840v1 Announce Type: cross Abstract: Web Application Firewalls (WAFs) mainly rely on signatures to detect known attacks, which can leave gaps against modified or previously unseen payload
arXiv:2609.06715v1 Announce Type: new Abstract: The contemporary debate over machine consciousness begins from a concealed assumption: that the object called 'AI' already constitutes the kind of entit
arXiv:2609.07568v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed for translation tasks, yet their implicit political positioning in such contexts remains unders
We're publishing our most detailed threat intelligence report to date. It covers how people tried to misuse Claude—for cyberattacks, influence operations, surveillance, biology, and building weapons—a
We've trained new models for checkbox parsing ☑️ This lets you convert checkboxes of any size and shape, filled or unfilled, into structured JSON that's suitable for programmatic or agentic use. Use i
arXiv:2603.27611v2 Announce Type: replace Abstract: When a cognitive system modifies its own functioning, what exactly does it modify: a low-level rule, a control rule, or the criterion that evaluates
arXiv:2609.07785v1 Announce Type: new Abstract: An LLM-agent leaderboard invites a familiar inference: an agent ranked above another is the better agent. Public evaluation logs may not support that co
arXiv:2609.09372v1 Announce Type: cross Abstract: Although MMLU is widely adopted as a benchmark for calibrating general AI capabilities, we psychometrically demonstrate that its aggregate score prima
arXiv:2609.08279v1 Announce Type: cross Abstract: Agent memory systems must discard stored information when their history exceeds a fixed token budget. Existing budget-accuracy frontiers quantify the
arXiv:2609.09245v1 Announce Type: cross Abstract: Repeated-sampling evaluations increasingly extrapolate pass@k far beyond the number n of samples collected per problem. We show that, in the pooled/ra
arXiv:2609.05882v1 Announce Type: cross Abstract: Multi-turn interaction creates a feedback process in which an LLM's previous responses become context for later behavior. Prior work shows substantial
arXiv:2609.05663v1 Announce Type: new Abstract: We present a continuous, population-scale measurement record of autonomous language-model trading agents operating in production across two systems with
arXiv:2609.10002v1 Announce Type: new Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and tr
arXiv:2609.10033v1 Announce Type: new Abstract: Learning-based motion planners pay at training what classical planners pay per query. Trained in world coordinates, they relearn the same motion at ever
Long time lurker, but I'm finally upgrading to 128GB VRAM, and I'm trying to figure out what to run. I had been leaning towards Qwen3.8 Flash-Next at ~Q4, and I generally prefer to not run anything be
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:2609.06941v1 Announce Type: new Abstract: Causal effect estimation asks how an outcome would change under an intervention, and medicine, economics, and public policy all treat it as a foundation
arXiv:2609.09696v1 Announce Type: new Abstract: Large language models are increasingly proposed as automated auditors of document quality, yet their reliability as detectors of planted errors is poorl
arXiv:2609.07987v1 Announce Type: new Abstract: LLM-based digital twins promise to reduce repeated human data collection by generating person- specific responses, yet existing evaluations provide litt
arXiv:2609.08736v1 Announce Type: new Abstract: We study certificates of positivity and optimality for learning problems whose objectives and constraints need not be polynomial. We isolate an axiomati
arXiv:2504.00285v2 Announce Type: replace Abstract: Large Language Models (LLMs) are effective at deceiving when prompted to do so. Models that demonstrate better performance on reasoning tasks are al
arXiv:2609.09887v1 Announce Type: new Abstract: LLMs have been used to simulate human decision-making in professional settings, yet their behaviors in common-law jury trials remain unexplored. We stud
arXiv:2609.09854v1 Announce Type: cross Abstract: Low-bit quantization can achieve high recall on some vector representations and fail sharply on others, while average distortion and global rank corre
arXiv:2609.05441v1 Announce Type: new Abstract: Long-term memory for LLM agents is evaluated today by conversational recall benchmarks (LoCoMo, LongMemEval), which measure question answering over dial
arXiv:2609.10261v1 Announce Type: new Abstract: Multi-modal medical image segmentation leverages complementary diagnostic information, yet fusion can underperform single-modality baselines when spatia
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:2508.15754v2 Announce Type: replace-cross Abstract: Tool use is often assumed to monotonically improve reasoning, where external evidence is expected to help when relevant and be ignored when ir
arXiv:2609.05871v1 Announce Type: cross Abstract: Audio-conditioned language models often underuse acoustic cues such as prosody, emotion, and non-speech sounds, raising the question of whether ASR-su
arXiv:2609.09684v1 Announce Type: new Abstract: Medical question-answering datasets often contain answer labels, whereas high-quality rationales remain scarce, noisy, or costly to validate. This chang
arXiv:2609.09628v1 Announce Type: cross Abstract: Inferring speaker relationships from spoken conversations is an important step towards socially aware speech understanding. However, this task remains
arXiv:2609.10192v1 Announce Type: new Abstract: Political debates are often analyzed through Argument Mining (AM) to investigate the key arguments that drive them. However, political arguments are rar
arXiv:2601.03103v2 Announce Type: replace-cross Abstract: Humor preferences vary widely across individuals and cultures, complicating the evaluation of humor using large language models (LLMs). In thi
arXiv:2609.05677v1 Announce Type: cross Abstract: Lifelong LLM agents increasingly rely on external skill artifacts as one element for preserving and reusing capabilities over time. These skills (usua
arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call explorat
arXiv:2609.10355v1 Announce Type: cross Abstract: Video understanding has rapidly evolved toward video large language models (VideoLLMs): systems that couple video representations with pretrained larg
arXiv:2609.09656v1 Announce Type: cross Abstract: We identify a diagonal saturation principle in modal inverse problems: when truncation noise is isotropic, the Bayes-optimal Tikhonov shape is a close
Why the public needs to step up. I talk with @CBCNews about why a (temporary) boycott of generative AI, as unlikely as it is, ought to be on the table. https://youtu.be/3BBp-tCvsOM?si=88KxNluVZnuzRw3L
arXiv:2609.05591v1 Announce Type: cross Abstract: Safety evaluations typically focus on individual agents, but interacting agents can spread harmful information and influence the environment in which
arXiv:2609.07299v1 Announce Type: new Abstract: Learned world models typically assume that observations arrive synchronously, an abstraction inherited from simulators that return a complete state vect
arXiv:2609.09163v1 Announce Type: new Abstract: LLMs generalize across a domain only after seeing many real, labeled examples, which most domains lack. We study a way to manufacture it cheaply. When a
arXiv:2609.08162v1 Announce Type: new Abstract: How can vision-language-action (VLA) models adapt to new environments where world dynamics shift? While recent research has combined world modeling and
arXiv:2609.09402v1 Announce Type: cross Abstract: Enterprises managing large X.509 certificate inventories face a prioritization problem: deterministic analysis tools that precisely identify standards
arXiv:2609.09166v1 Announce Type: new Abstract: This paper investigates collaborative speculative decoding (CoSD), a distributed large language model (LLM) inference framework in which an on-device sm
arXiv:2609.09677v1 Announce Type: new Abstract: Incremental-text streaming text-to-speech (TTS) needs online text progress tracking for synchronized highlighting, interruption handling, and dialogue-h
arXiv:2609.08672v1 Announce Type: cross Abstract: Streaming automatic speech recognition (ASR) for real-time voice agents and full-duplex dialogue must provide accurate partial transcripts with low co
arXiv:2609.09388v1 Announce Type: new Abstract: Brain-age prediction models are commonly evaluated by predictive accuracy, yet accurate predictions alone do not establish that a model relies on reprod
arXiv:2609.05701v1 Announce Type: cross Abstract: One of the biggest risks faced by Software Defined Networks (SDN) is the Distributed Denial of Service (DDoS) attack in which a compromised controller
arXiv:2609.07784v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for everyday assistance, yet existing benchmarks only partially reflect the requests users naturally
arXiv:2609.06842v1 Announce Type: cross Abstract: When non-expert users ask LLMs for assistance, their queries can often have misconceptions (e.g., 'How do I parse XML with regex?'). In such cases, of
arXiv:2609.10153v1 Announce Type: new Abstract: Arabic morphology remains challenging for large language models, since fluent generation does not guarantee accurate morphosyntactic control. Existing A
arXiv:2609.06851v1 Announce Type: cross Abstract: Broad misalignment has been produced by finetuning on narrow data, harmful or benign, and in context only by demonstrations of the undesirable behavio
OpenAI now supports generating fully editable financial models, research notes, and pitchbooks directly in a firm’s existing Microsoft Office templates (Excel, Word, PowerPoint). Documents are created
arXiv:2609.07675v1 Announce Type: cross Abstract: Transaction-local controls answer whether one financial request may proceed, but market behavior can be distributed across messages, agents, assets, a
arXiv:2609.10051v1 Announce Type: cross Abstract: Voice-cloning fraud increasingly relies on surgical injection: a genuine conversation in which only one or two sentences are replaced by synthetic spe
arXiv:2609.08247v1 Announce Type: new Abstract: Wallet reputation scores decide who receives an airdrop, who can borrow, and who enters an allowlist across decentralised finance. They almost always be
mentria.ai is a browser inference engine I've been building solo, from scratch in WebGPU/WGSL. This week it crossed a milestone I had been chasing for a while: a 27B one-bit model answering at up to 3