Knowledge catalogue
arXiv:2609.11042v1 Announce Type: new Abstract: Agent usage is shifting toward long-horizon tasks such as coding and scientific discovery, among which terminal tasks are especially important. We intro
arXiv:2609.09395v1 Announce Type: new Abstract: Language models act through tools, yet practical agents face libraries containing thousands of interfaces. We introduce the tool menu as the short, orde
arXiv:2609.11770v1 Announce Type: new Abstract: Large language models are superseded every few quarters; clinical evidence takes years. We asked whether medical research is keeping pace with the syste
arXiv:2609.10613v1 Announce Type: cross Abstract: In-context learning (ICL) jailbreaks reveal a critical vulnerability in multimodal large language models (MLLMs): harmful demonstrations in the prompt
arXiv:2609.09263v1 Announce Type: cross Abstract: Speech-to-speech (S2S) models now run inside dubbing, translation, and voice agents. Unlike text models, they hear the speaker's voice, which carries
arXiv:2609.10263v1 Announce Type: new Abstract: Persistent language agents need stored experience to remain available across time, while each answer requires evidence suited to a particular question.
arXiv:2609.09707v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) applies a uniform cross-entropy loss to all target tokens, even though different tokens provide unequal learning signals fo
I'm currently building my system around 3060s, but I might be able to get a 4060 for a nice deal. At first it seemed like a no brainer, but turns out the 4060 has lower memory bandwidth. In a system t
arXiv:2609.07075v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is commonly evaluated by whether the final answer is correct. That test is insufficient: an answer can match its re
arXiv:2609.07719v1 Announce Type: new Abstract: Medical imaging artificial intelligence (AI) is commonly developed as separate mappings from radiographs to diagnostic outputs or from clinical descript
arXiv:2609.06573v1 Announce Type: new Abstract: Recent studies report that automated red-teaming finds more vulnerabilities, at lower cost, than human red-teaming on standard AI safety benchmarks, and
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:2609.10142v1 Announce Type: new Abstract: Large language models remain fragile against malicious fine-tuning, motivating training-time defenses against harmful persona drift. Preventative Steeri
arXiv:2609.07672v1 Announce Type: new Abstract: Production content-generation systems must integrate a user's immediate task, long-term brand identity, historical evidence, and revision feedback. We p
arXiv:2609.08248v1 Announce Type: new Abstract: Modern industrial ads ranking stacks are increasingly bottlenecked not by model capacity or training compute, but by the throughput of human ML iteratio
arXiv:2609.05995v1 Announce Type: new Abstract: Achieving reliable autonomy in the wild requires agents to sustain continuous operations across long-horizon trajectories. However, as agents navigate t
arXiv:2609.08166v1 Announce Type: cross Abstract: The twenty-first century's transformative technology, artificial intelligence, is increasingly constrained by the twentieth century's transformative t
arXiv:2609.07152v1 Announce Type: new Abstract: Goal-oriented conversational systems must answer factual questions, understand visitor-provided information, and advance business objectives without bec
arXiv:2603.01690v3 Announce Type: replace-cross Abstract: While dense biomedical embeddings achieve strong performance, their opaque dimensions limit transparency in biomedical NLP. Recent question-ba
arXiv:2609.08318v1 Announce Type: cross Abstract: The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE tasks
arXiv:2609.09356v1 Announce Type: new Abstract: At Noora Health, our nurses answer more than 50,000 medical queries per month on our WhatsApp-based service that provides caregivers with on-demand supp
arXiv:2609.06366v1 Announce Type: new Abstract: Scientific discovery in data-rich domains is currently constrained by human bandwidth: the growth in the volume and complexity of real-world data far ou
arXiv:2608.00745v2 Announce Type: replace Abstract: Modern endpoint detection systems face a fundamental tension: signature-based approaches are trivially evaded by polymorphic or adaptive threats, wh
arXiv:2609.10445v1 Announce Type: new Abstract: Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: mo
arXiv:2609.10410v1 Announce Type: new Abstract: The growing complexity of content moderation policies presents a critical challenge for their consistent operationalization. While foundation models pos
arXiv:2609.09766v1 Announce Type: new Abstract: Churn models typically identify high-risk customers but do not specify which feasible retention action should be considered or why that action is approp
arXiv:2609.08094v1 Announce Type: new Abstract: Large Language Models are increasingly deployed in public-sector settings, where incorrect guidance can cause irreversible harm. We introduce CIVI, the
arXiv:2609.09134v1 Announce Type: new Abstract: Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic
arXiv:2606.18425v2 Announce Type: replace-cross Abstract: Federated learning over medical images is a demanding workflow application. Each round fans out across parallel client jobs and converges on a
arXiv:2609.06126v1 Announce Type: new Abstract: We introduce Personalized and Reliable Popular Science Writing, a novel task that requires adapting scientific explanations to audiences with different
arXiv:2609.09901v1 Announce Type: new Abstract: Large language models often repeatedly select the same answer even when many alternatives are plausible. Prior work treats this concentration as bias, b
arXiv:2609.09241v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling model capacity while preserving efficient inference in large fo
arXiv:2609.09433v1 Announce Type: new Abstract: Leave-One-Subject-Out (LOSO) evaluation estimates generalisation performance for subject-based classification but makes Neural Architecture Search (NAS)
arXiv:2609.09721v1 Announce Type: new Abstract: Low-bit attention accelerates Transformer inference by moving the QK^op and PV matrix multiplications to FP8 or FP4 matrix engines. However, the softmax
arXiv:2608.27824v2 Announce Type: replace Abstract: Evidential argumentation extends Dung's abstract argumentation by requiring arguments and interactions to be backed by chains of evidence rooted in
arXiv:2609.09133v1 Announce Type: new Abstract: Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agent
I believe I may currently hold the record for memory constrained inference for Qwen3.8–Flash-Next on Apple Silicon — needing only about 21GB of allocations. Introducing Cherenkov, an inference engine
arXiv:2609.06095v1 Announce Type: cross Abstract: Motivation: Undergraduate computing students increasingly turn to generative AI (GenAI) tools to understand abstract concepts through analogies. Analo
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:2609.06036v1 Announce Type: new Abstract: Proposal-based controllers---learned policies, language-model planners, and other black-box generators---are increasingly deployed behind runtime verifi
Great paper from AWS. I use a similar setup where an agent orchestrator sits on top of a multi-agent system. (bookmark it) This work introduces one of the many approaches available to manage compound
arXiv:2609.10225v1 Announce Type: new Abstract: Feature transformation improves predictive performance on tabular data by constructing informative abstractions from raw features. Recent generative app
arXiv:2609.07353v1 Announce Type: new Abstract: Large language models (LLMs) are used to simulate human participants in psychological research. We asked whether LLMs that reproduce human evaluations o
// human-values.pseudo | ARTIFACT 0.1.0-experimental.1 | BASE 1.2.0-rc1 | EDITION ai-compact | NARRATOR System_Synthesis_Node_01 | PROVENANCE human-directed, AI-assisted | STATUS single-encoder resear
arXiv:2609.06960v1 Announce Type: new Abstract: Invasive neural recordings provide high-fidelity measurements of brain activity, with signals such as intracranial EEG (iEEG) and intracortical spiking
arXiv:2609.08082v1 Announce Type: new Abstract: Preference-based fine-tuning methods such as RLHF and DPO require substantial compute and large preference datasets. They also need direct access to the
arXiv:2606.13945v2 Announce Type: replace Abstract: Rare diseases affect over 300 million patients across more than 7{,}000 conditions, yet no single hospital encounters enough cases of any one condit
arXiv:2609.08273v1 Announce Type: new Abstract: Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuou
arXiv:2609.09907v1 Announce Type: new Abstract: Meta-learning has emerged as an effective paradigm for transferring knowledge across sequential bandit tasks. While substantial progress has been made f
arXiv:2507.15393v2 Announce Type: replace-cross Abstract: Phishing email is a critical step in the cybercrime kill chain due to the high reachability of victims' email accounts and the low cost of lau
arXiv:2609.09776v1 Announce Type: cross Abstract: Frontier gains in language-model reasoning come from reinforcement learning on reasoning traces and are concentrated in domains with a cheap, sound ve
arXiv:2609.08372v2 Announce Type: replace Abstract: A dense retriever encodes a question as one vector, but the question arrives one word at a time. We read 2,144 held-out headlines from Thu Vien Phap
arXiv:2609.05721v1 Announce Type: new Abstract: Understanding whether language-model embeddings encode structured real-world information is important for both representation analysis and information r
arXiv:2602.06471v2 Announce Type: replace Abstract: The architectural shape of dense Transformers has remained remarkably stable: narrow-wide-narrow feed-forward networks (FFNs) consume most non-embed
arXiv:2609.10464v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architecture (JEPA) world models learn a compact latent representation of the world that supports prediction and planning,
arXiv:2609.06647v1 Announce Type: new Abstract: Although professional workflows leverage large language models widely, the interpretation for auditing unconstrained free-text generation is usually int
arXiv:2609.09233v1 Announce Type: cross Abstract: How can language model agents effectively leverage libraries of reusable knowledge to solve long-horizon tasks? Recent work has increasingly focused o
arXiv:2609.08226v1 Announce Type: new Abstract: Temporal graph learning models the evolution of dynamic systems, where both structural interactions and semantic states change over time. However, exist
arXiv:2609.05920v1 Announce Type: cross Abstract: Agent Skills combine instructions with files, packages, tools, models, and services, so operational identity can exceed a signed directory. Recursive
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