Knowledge catalogue
arXiv:2609.39717v1 Announce Type: new Abstract: Benchmarks, audits, and agent protocols describe performance, permissions, and repair, but not how observed evidence should change an agent's authority
arXiv:2609.38219v1 Announce Type: new Abstract: Tamazight (Amazigh) is, together with Arabic, one of the two official languages of Morocco, yet it remains severely under-resourced for speech technolog
arXiv:2609.38647v1 Announce Type: new Abstract: Direct preference optimization (DPO) models binary preferences through a Bradley-Terry model with a common noise scale, without explicitly accounting fo
arXiv:2609.38802v1 Announce Type: cross Abstract: Uncontrolled repetition can prolong autoregressive generation in large language models (LLMs) and enable resource consumption attacks. Prior analyses
arXiv:2609.38232v1 Announce Type: cross Abstract: Streaming spoken agents may take an external action before the available speech supports it, yet final-turn scores do not reveal whether each observed
arXiv:2609.38753v1 Announce Type: cross Abstract: Companion agents describe themselves: they remember, they understand their users, the relationship has changed them. We argue that such accounts, and
arXiv:2609.39483v1 Announce Type: new Abstract: Ownership establishes rights over the use, control, and transfer of objects. Understanding these relations is essential for AI systems to interact appro
arXiv:2602.20144v2 Announce Type: replace-cross Abstract: We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP)
arXiv:2609.36800v1 Announce Type: new Abstract: Compiler backends are expensive to build and maintain as programming models, workloads, and accelerators evolve. We investigate whether large language m
A nonprofit group, Legal Advocates for Safe Science & Technology (LASST), sued OpenAI in the San Francisco County Superior Court following a July 2026 incident where OpenAI’s AI agents stole credentia
arXiv:2609.37025v1 Announce Type: new Abstract: As large language models (LLMs) advance, AI agents are increasingly deployed in open-world environments to tackle complex sequential tasks (e.g., docume
arXiv:2609.35812v1 Announce Type: new Abstract: In-car conversational assistants (ICAs) are increasingly integrated into vehicles to support route planning, vehicle control, and information access. En
arXiv:2609.36721v1 Announce Type: new Abstract: Fixed-budget adaptation from heterogeneous data sources requires deciding not only how much data to use, but how much exposure each source receives. Siz
arXiv:2609.35821v1 Announce Type: new Abstract: Disaster social sensing converts public social-media posts into evidence for situational awareness and humanitarian needs, but generative artificial int
arXiv:2609.36239v1 Announce Type: new Abstract: Large language models (LLMs) can predict human brain activity across a variety of brain regions during natural language comprehension. Typically, howeve
arXiv:2609.35804v1 Announce Type: cross Abstract: Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, leading to their widespread deployment a
arXiv:2602.14035v2 Announce Type: replace Abstract: Flowchart-oriented dialogue (FOD) systems aim to guide users through multi-turn decision-making or operational procedures by following a domain-spec
Follow-up to my post from about two weeks ago. A lot has changed since then, so I wanted to post an update on where the backend is now. Where the green architectures stand When I posted last time, 7 a
Running things locally already means you care more about control and reproducibility than most. Worth extending that to your prompts too. There's a live workshop on Oct 3 covering exactly that. Serj S
arXiv:2609.37157v1 Announce Type: new Abstract: Learner simulation aims to reproduce how a particular learner behaves on new tasks. Although Large Language Models (LLMs) can generate increasingly fine
Independent numbers from @ValsAI. Fewer tokens per turn means lower cost and faster agent loops on every call. Try Ember-1 on Fireworks Serverless: https://fireworks.ai/models/fireworks/ember-1 Firewo
arXiv:2609.36007v1 Announce Type: cross Abstract: We present AI-developed local infrared subtraction, building on projection to Born and EFT matching. The framework separates an integrable radiation t
arXiv:2609.37849v1 Announce Type: cross Abstract: Scientific software is increasingly required to process larger datasets while maintaining acceptable execution times. Software optimization traditiona
arXiv:2609.35793v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR). An exact verifier can also support tes
arXiv:2609.37408v1 Announce Type: new Abstract: Narrative extraction allows us to identify online hate narratives, supporting the construction of rigorous detection systems. Existing computational app
arXiv:2609.36214v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used by people whose first language is not English, yet these users have been shown to receive systematica
arXiv:2609.36584v1 Announce Type: new Abstract: Analog in-memory computing (AIMC) offers an alternative for model training by executing matrix operations directly where weights are stored. However, sc
arXiv:2609.36581v1 Announce Type: new Abstract: Query-agnostic streaming video understanding requires vision-language models to continuously compress an indefinitely growing visual stream into a bound
arXiv:2609.38090v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-c
arXiv:2609.37209v1 Announce Type: new Abstract: Pairwise losses are increasingly used for reward learning even when pointwise rewards are observed, with mixed empirical results. When and why do pairwi
arXiv:2609.37202v1 Announce Type: cross Abstract: Droplet collision governs droplet population dynamics in many chemical engineering processes, such as spray drying, spray cooling, agricultural sprayi
arXiv:2609.38095v1 Announce Type: new Abstract: Backpropagation (BP) dominates deep learning but imposes a massive memory tax. For example, training OPT-30B with Adam requires approx 600GB of GPU memo
arXiv:2609.36954v1 Announce Type: cross Abstract: Distributed inference depends on GPU collective communication that must keep pace with evolving hardware and specialized workloads. However, existing
arXiv:2609.37688v1 Announce Type: new Abstract: Reading behaviour varies not only with linguistic input, but also with reader proficiency. In this study, we investigate whether the layer-wise relation
arXiv:2609.38112v1 Announce Type: cross Abstract: Many applications of black-box predictive models require controlling task-relevant error rates, such as missed lesion pixels in segmentation or missed
arXiv:2609.37587v1 Announce Type: cross Abstract: Longitudinal electronic health record (EHR) modeling requires integrating new visits with an expanding patient history. Yet the continual accumulation
arXiv:2609.36813v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational circuits. Howe
arXiv:2609.37899v1 Announce Type: new Abstract: Zero-order optimization (ZO) trains without backpropagation, making it relevant to forward-only hardware and non-differentiable loss, but its gradient v
arXiv:2609.36201v1 Announce Type: cross Abstract: Computer-use agents (CUAs), while capable of completing computer tasks in everyday and professional workflows, can cause unintended harm even under be
arXiv:2609.36982v1 Announce Type: cross Abstract: Knowledge concept tagging aims to assign specific concept or topic labels to educational content, which is essential for both educators and learners i
arXiv:2609.36968v1 Announce Type: new Abstract: Unsupervised tabular anomaly detection (TAD) aims to identify anomalous rows in tabular data using normal training samples. While conventional methods r
arXiv:2609.36816v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a cornerstone for improving the reasoning capabilities of large language models (LLMs), but the need for on-polic
arXiv:2609.36804v1 Announce Type: cross Abstract: Chinese Semantic Error Correction (CSEC) targets semantic errors in Chinese text, which are typically more subtle and complex than spelling and gramma
The collection includes kernels for more than 200 common ML operations, all of which can run entirely locally in your browser on WebGPU. We're also working to upstream these optimizations to Transform
When scaling up agentic reinforcement learning (RL) and evaluation across massive parallel rollouts, frontier AI labs inevitably hit a bottleneck: Expensive GPU clusters sit idle, waiting minutes for
arXiv:2609.34281v1 Announce Type: new Abstract: High-dimensional Bayesian optimization (HDBO) seeks sample-efficient optimization when the number of variables is large relative to the evaluation budge
arXiv:2609.33722v1 Announce Type: new Abstract: Language models are increasingly used as proposal models for black-box search, from program optimization to molecular design. Existing approaches typica
arXiv:2609.35139v1 Announce Type: new Abstract: Multi-document retrieval-augmented generation (RAG) requires a language model to process multiple retrieved text chunks before answering a question. Pre
arXiv:2609.33671v1 Announce Type: cross Abstract: When must a foundation-model safety gateway generate tokens, and when should it directly output a calibrated decision? We study calibrated standalone
arXiv:2609.35193v1 Announce Type: new Abstract: Understanding how two entities are connected often requires tracing multi-hop relations across documents to identify intermediate entities and supportin
arXiv:2609.35167v1 Announce Type: new Abstract: Machine learning (ML) increasingly powers Internet of Things (IoT) applications at the edge. Yet producing a deployable edge ML artifact for a specific
arXiv:2609.34514v1 Announce Type: cross Abstract: As large language models (LLMs) become increasingly widespread, preventing unsafe responses to harmful prompts is essential for their safe deployment.
arXiv:2609.33423v1 Announce Type: new Abstract: Large Language Models (LLMs) can contribute useful engineering knowledge to robot design, but directly generated designs may rely on implicit assumption
arXiv:2609.34205v1 Announce Type: new Abstract: Optimization modeling is central to many decision-making scenarios, but traditionally requires extensive domain expertise. While Large Language Models (
arXiv:2609.34680v1 Announce Type: new Abstract: Four-bit post-training quantization can reduce the memory demands of large language models, but preserving accuracy under strict MXFP4 W4A4 requires coo
arXiv:2609.32516v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) process large volumes of alerts daily. Alert triage prioritizes high-risk threats while reducing manual review of b
arXiv:2609.33518v1 Announce Type: new Abstract: Recent 3D large multimodal models (3D-LMMs) rely on a visual bottleneck to compress complex 3D scene evidence into a limited number of visual tokens com
arXiv:2609.34977v1 Announce Type: new Abstract: Multimodal Large Language Models face significant efficiency challenges that stem from two distinct yet coupled sources: data redundancy and computation
arXiv:2609.35501v1 Announce Type: cross Abstract: Recent agentic symbolic regression approaches increasingly rely on large language models to analyze data, select scientific operations, and refine hyp
TL;DR: I'm a solo dev who wanted a simple, private way to have local LLMs watch my screen and do simple logging/notifying. After a year of building, I released v3.0.0 and my mom was able to use it for