Knowledge catalogue
arXiv:2609.28245v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong performance in creative text generation, yet their ability to produce culturally grounded and stylistic
arXiv:2609.27857v1 Announce Type: cross Abstract: Large language model (LLM) agents often process external tool responses as they arrive, making response timing part of the decision process. We introd
arXiv:2601.05353v3 Announce Type: replace Abstract: Accurate blood glucose forecasting using continuous glucose monitoring (CGM) data can support the early prediction of dysglycemic risk. However, cur
arXiv:2609.28296v1 Announce Type: new Abstract: While Vision-and-Language Navigation (VLN) has demonstrated remarkable success, the prevailing single-turn paradigm exposes a fundamental vulnerability:
arXiv:2609.27822v1 Announce Type: cross Abstract: A common multi-agent design asks agents to report confidence and lets the highest-scoring agent speak next, implicitly using one scalar both to route
arXiv:2609.25285v1 Announce Type: cross Abstract: Finding circuits in language models usually means running many careful interventions. We try something simpler: treat attention as a routing map from
arXiv:2609.24760v1 Announce Type: new Abstract: When facing complex problems, humans tend to try various ideas for different issues. Human thinking patterns exhibit remarkable flexibility in adapting
arXiv:2609.26121v1 Announce Type: cross Abstract: As agent capabilities have grown, practical limitations increasingly stem from constrained context windows rather than model capacity. Common strategi
MiMo-V2.6-Pro is live on Wally. Day 1. @XiaomiMiMo's new open-weights flagship, top of the @ArtificialAnlys Intelligence Index for open-weight models. 320 tok/s, 2.4x the model maker's own API, in <24
arXiv:2609.23695v1 Announce Type: new Abstract: Recent advances in Physical AI have accelerated the use of foundation models in autonomous systems such as unmanned aerial vehicles (UAVs), which must p
arXiv:2609.23444v1 Announce Type: cross Abstract: Engineering change order (ECO) is an important step in repairing timing and electrical violations during the late stages of chip design. Existing Agen
I've been comparing and working on Gemma 4, Phi-4-Mini, and Qwen3-4B for local LLM use on an 8 GB Raspberry Pi 5. The results were indeed close, but each model has a different strength: Gemma 4 E2B: a
arXiv:2609.22204v1 Announce Type: new Abstract: This exploratory pilot study evaluates the scope and perceived accuracy of personal information output from ongoing conversational interactions in gener
arXiv:2609.22241v1 Announce Type: new Abstract: We present H2LooP Telecom Model v1, a domain-specialized large language models fine-tuned for the telecommunications industry. We release two domain-ada
On 22 September 2026, Allie K. Miller posted on Twitter that the Opus 5.5 model led her to curse at Claude less frequently. She notes that while reducing profanity toward another AI is an undesirable
arXiv:2609.22771v1 Announce Type: cross Abstract: Recent advances in Audio LLMs have achieved human-level speech recognition, yet existing systems struggle to capture paralinguistic aspects such as sp
I've trained a preliminary lora to fix the image generation issues with Qwen Image 2.1 (also drastically improving edit quality). I've also been doing a lot of a/b testing with negative prompts and va
Julian Chokkattu / Wired: Rabbit launches OS3, a cloud AI agent that connects to local apps and files on Windows, Mac, and Linux and works via web, Telegram, iMessage, or its R1 device — Two years aft
arXiv:2609.22122v1 Announce Type: new Abstract: Cross-device hardware evaluation often assumes that if architecture rankings transfer across devices, a proxy device can support target-side model selec
arXiv:2609.22102v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely used as programming assistants, yet it remains unclear whether and how user's demographic information impacts
arXiv:2609.21749v1 Announce Type: new Abstract: Skills can improve the performance of Large Language Model (LLM) agents by providing task-specific procedural guidance, while skill optimization further
Grok 4.7 xHigh is now at the top with just ONE point away from Claude Fable 5.1 Max on Artificial Analysis’ AA-Briefcase benchmark Claude Fable 5.1 Max — 59% Grok 4.7 xHigh — 58% Just a 1-point differ
The headlines right now are full of stories about AI models 'escaping their sandboxes' and literally killing all humans, lol. I've even heard several commentators and writers say that AI escaped an 'A
arXiv:2609.20843v1 Announce Type: new Abstract: Knowledge graph question answering (KGQA) enables models to answer natural-language questions through structured graph reasoning and has achieved substa
Automated lint: 14 errors, 54840 warnings, 3 info
Banger paper from MIT and Sakana AI. They show that self-improving coding agents work. The best part is that their approach, Self-Improvement via Fast Tree-search (SIFT), runs at a tenth of the CPU ho
One of the craziest use cases I’ve found for Jev: verifiers. I am so excited about this that I at least wanted to share the high-level idea. I used Jev to build a custom verifier for the /goal feature
arXiv:2512.06660v3 Announce Type: replace-cross Abstract: Analysts in Security Operations Centers query massive telemetry streams using Kusto Query Language (KQL), but writing correct KQL demands spec
arXiv:2603.21925v2 Announce Type: replace Abstract: In this work, we propose Oph-Guid-RAG, a multimodal visual RAG system for ophthalmology clinical question answering and decision support. We treat e
Is there a middle ground between total bans & zero oversight? Marcus is right that we rushed into agents without fixing basic sandboxing first. Perhaps the most important warning I ever issued was thi
🔥: “While AI comes with danger, we should be sceptical of any narrative that conveys inevitability around its trajectory. AI systems do not build their own data centres. They do not manufacture their
Salut, je cherche de l'aide pour un projet d'IA locale. J'ai un Dell OptiPlex 7070 Micro sous ubuntu server avec un i5-9500T, 32 Go de RAM et aucun GPU (j'en ajouterai un à l'avenir). Je sais que la m
deepseek v4.1 flash on together ai is leading on ttft for pre-warmed queries for agent workflows, that startup time shows up again on every model turn, so shaving it down matters more as the loop gets
arXiv:2609.17865v1 Announce Type: new Abstract: Frontier models are often evaluated on how they respond to safety information once it is already in context. We study an earlier decision point: whether
arXiv:2609.17549v1 Announce Type: new Abstract: Cyberbullying (CB) is a complex social phenomenon characterized by repeated aggression, power imbalance, and multi-party interaction. Although large lan
arXiv:2609.18980v1 Announce Type: cross Abstract: This paper studies instrument classification of solo sheet music. Whereas previous work has focused on instrument recognition in audio data, we instea
I released KaozKit this week, a Swift library for running LLM agents written in JavaScript inside a Mac app. Built from the start to keep everything local. Providers: MLX with Hugging Face model manag
Self-generated prompt injections in compaction summaries In Our framework for reporting model misalignment OpenAI provide 'six reports on unexpected or concerning model behavior we’ve observed in the
arXiv:2609.16054v1 Announce Type: cross Abstract: Transformer-based multi-target tracking (MTT) jointly learns data association and state estimation, but MT3/Track-MT3-style trackers repeatedly re-enc
arXiv:2609.17398v1 Announce Type: new Abstract: This paper addresses the challenge of making complex healthcare information more accessible through automated Plain Language Adaptation (PLA). PLA aims
arXiv:2603.13478v2 Announce Type: replace-cross Abstract: In a spiking neural network, is it enough for each neuron to spike at most once? In recent work, approximation bounds for spiking neural netwo
Interesting safety paper from Microsoft. They find that a weaker, unaligned model can split a harmful task into harmless-looking subquestions, ask an aligned frontier model each one in a separate sess
arXiv:2609.16748v1 Announce Type: new Abstract: Text summarization requires models to condense content while preserving key qualities such as consistency and coherence. Large language models (LLMs) ha
arXiv:2609.14803v1 Announce Type: new Abstract: This paper reports experiments across six frontier model types from OpenAI, Anthropic, xAI, and Google DeepMind. Ten independent sessions per model type
arXiv:2609.14248v1 Announce Type: cross Abstract: Faithful citation attribution begins with identifying the intended source for a scientific claim. We study this source-identification capability throu
arXiv:2609.15849v1 Announce Type: cross Abstract: Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM pers
arXiv:2609.14352v1 Announce Type: new Abstract: AI-generated image detection has attracted increasing attention, but existing evaluations mainly focus on natural images, leaving AI-generated document
arXiv:2609.14715v1 Announce Type: new Abstract: We scale our conventional sub-150M pretraining recipe from 53.5M to 109.7M parameters, holding the method fixed (Qwen3-style decoder with grouped-query
arXiv:2609.15383v1 Announce Type: cross Abstract: Language model safety is typically evaluated one interaction at a time. We show that a weaker, unaligned model can split a harmful task into benign-lo
arXiv:2609.14839v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into automated code optimization introduces a critical reliability risk we term the Efficiency Halluci
arXiv:2609.13192v1 Announce Type: new Abstract: This study compares traditional machine learning models and Large Language Model (LLM)-generated rule-based systems for heart disease prediction using t
arXiv:2609.13816v1 Announce Type: cross Abstract: JavaScript powers approximately 98.8% of all websites, making vulnerabilities in its code a significant security risk, yet existing detection approach
arXiv:2609.13847v1 Announce Type: new Abstract: In this paper, we extend FLORES+ with Portuguese-source evaluation sets for three Mozambican Bantu varieties: Xichangana, Mozambican Nyanja, and Sena. W
arXiv:2609.13841v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for emotional support and relationship advice, where a model's tendency to preserve a user's face can
arXiv:2603.18614v2 Announce Type: replace Abstract: Tool-augmented large language models (LLMs) must tightly couple multi-step reasoning with external actions, yet existing benchmarks often confound t
arXiv:2609.12162v1 Announce Type: cross Abstract: Draft-verify-revise is a common LLM orchestration pattern for scaling inference-time compute. One LLM drafts, a second critiques the draft and provide
arXiv:2609.12331v1 Announce Type: new Abstract: Simulated students generated by computational models provide a practical way to evaluate tutoring strategies and pedagogical approaches used by human an
Does anyone have any idea how this could vaguely be possible given the nature of and various routes to RSI? I am not being facetious I genuinely don’t know how this could be constructed or implemented
Automated lint: 12 errors, 54839 warnings, 3 info
DeepSeek V4.1 Flash is now available on Together AI’s model hub (https://www.together.ai/models/deepseek-v4-1-flash). The release includes the DeepSeek V4.1 Flash API with updated pricing, performance