Knowledge catalogue
Nos travaux déplaisent à certaines petites frappes. Celui-là est candidat à l’élection présidentielle 😅 Cédric O, ancien ministre du numérique d'Emmanuel Macron, détient 90 millions d'euros en portefe
I am trying to learn more about long-term memory and how people are handling that nowadays. Historically, I have used a mixture of paid cloud AI services (ChatGPT, Gemini, OpenRouter API) and my own l
Just find it interesting, since if Taalas tried to get into the consumer market, it could be interesting. Kind of like how we have game discs on CDs. Of course, a Qwen3.8-27B chip is stuck on 3.8-27B,
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
Cédric Villani après l'annonce de la solution d'OpenAI au problème du millénaire : « J’ai été secoué. Une ambiance de fin de l’histoire. C’est un cataclysme comme jamais les maths n’en ont connu. » Cé
Inference scaling part 1. Starting with a modded text generation function (temperature scaling, top-p filtering, multinomial sampling) to generate diverse outputs for self-consistency and best-of-N (i
Hi just wondering has anyone submitted anything to JMLR before? Especially in the last 2 years? What is the experience like? Background: I am a Comp Sci PhD student, but my secondary supervisor (the o
arXiv:2609.19334v1 Announce Type: new Abstract: Full-duplex speech-to-speech (S2S) models provide natural, low-latency conversational interaction and would benefit from the ability to use external too
arXiv:2609.20804v1 Announce Type: new Abstract: Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work t
arXiv:2609.19199v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly adopted for compliance and legal reasoning tasks, yet their outputs often lack explicit grounding in leg
arXiv:2609.19189v1 Announce Type: cross Abstract: Design verification remains one of the most resource-intensive stages of hardware development, often consuming up to 70% of the total design effort. W
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:2609.19491v1 Announce Type: cross Abstract: Modern LLMs and AI agents increasingly support data engineering workflows that integrate evidence from unstructured sources. Such pipelines typically
arXiv:2609.20004v1 Announce Type: cross Abstract: Reward-based reinforcement learning for language models, exemplified by Group Relative Policy Optimization (GRPO), collapses an entire stochastic traj
arXiv:2508.06734v3 Announce Type: replace-cross Abstract: While graph-based Android malware classifiers report strong benchmark accuracy of over 94%, their performance sharply decreases up to 45% when
arXiv:2609.19152v1 Announce Type: new Abstract: Misinformation detection tools often rely on binary true and false classifications or models trained on historical examples, limiting their usefulness w
Been building this for a few months, mostly for myself, and it just got a proper release so figured I'd post it. It's a native GGUF inference runtime with OpenAI/Anthropic-compatible APIs and a chat U
arXiv:2609.19413v1 Announce Type: cross Abstract: Robot manipulation policies are improving quickly, and real-robot evaluation remains the standard evidence for that progress. It still relies on a hum
arXiv:2507.10059v2 Announce Type: replace Abstract: Large Language Models have achieved remarkable performance across a large number of tasks, but face critical deployment and usage barriers due to su
arXiv:2609.20250v1 Announce Type: new Abstract: Zero-shot essay scoring with large language models is usually demonstrated with proprietary API models, yet the settings where automated scoring is most
I've seen people describe Jev as an 'AI if statement'. But what if it actually WAS an if statement? Introducing Probably: a programming language powered by Jev: https://probably-lang.southpolesteve.wo
arXiv:2609.20543v1 Announce Type: new Abstract: Full-consensus rates are often treated as indicators of collective cognition, yet depend on how participation and final states are operationalized. We r
arXiv:2609.19541v1 Announce Type: new Abstract: Conventional robot planning methods seek collision-free paths to a goal but fail when all paths are blocked. In these cases, the robot must determine wh
arXiv:2609.19513v1 Announce Type: new Abstract: High-quality pre-training data is a critical bottleneck for educational and STEM-specific language models targeting edge AI and on-device deployment whe
arXiv:2505.16180v3 Announce Type: replace-cross Abstract: Evaluating image captions requires cohesive assessment of both visual semantics and language pragmatics, which is often not entirely captured
arXiv:2609.20398v1 Announce Type: new Abstract: Semantic parsing (SP)-based knowledge base question answering aims to answer natural language questions by generating executable logical forms (LFs) ove
arXiv:2609.19483v1 Announce Type: new Abstract: Text-based person retrieval under a sim-to-real gap (synthetic training data, a real-image gallery) is usually tackled with costly fine-tuned cross-enco
arXiv:2609.19526v1 Announce Type: new Abstract: Coding agents can recursively modify their own implementations, forming a loop of self-improvement. While prior work shows this can boost performance on
arXiv:2609.20565v1 Announce Type: new Abstract: Recent advancements in large language models have revolutionized the field of psychological counseling, especially in the context of Cognitive Behaviora
arXiv:2609.20712v1 Announce Type: new Abstract: This paper introduces and operationalizes summarization bias: a proposed systematic tendency of large language models (LLMs) to represent narrative mean
Super interesting work from Zoom and colleagues. If you maintain a hand-built coding harness, there are some great insights here. (bookmark it) They held the execution loop of a coding harness fixed a
arXiv:2609.19616v1 Announce Type: new Abstract: Complexity measured from generated code is failure-dependent: a difficult prompt can yield a short failing program and be assigned low output complexity
arXiv:2609.19924v1 Announce Type: cross Abstract: Large Language Models (LLMs) transform vast collections of unstructured text into semantic patterns used for language generation and reasoning tasks.
arXiv:2609.18366v1 Announce Type: new Abstract: Reliable agent evaluation is complicated by automatic harness optimization, which repeatedly uses a released benchmark B_{rel} to guide a Proposer that
arXiv:2609.18273v1 Announce Type: new Abstract: Web browsing often appears ephemeral: users visit a few websites, complete a task, and move on. However, even short fragments of browsing activity can c
arXiv:2609.19071v1 Announce Type: new Abstract: Extracting SNP-phenotype associations from biomedical literature is vital but challenging. We benchmarked diverse NLP models, including MLMs, hybrid arc
arXiv:2609.18515v1 Announce Type: new Abstract: Safety alignment teaches large language models (LLMs) to recognize harmful requests and reject risky instructions. Yet aligned models can fail when harm
arXiv:2609.17564v1 Announce Type: new Abstract: Deploying retrieval-augmented generation (RAG) on commodity GPUs such as the NVIDIA T4 (16 GB VRAM) exposes a practical failure mode we call the Compres
arXiv:2609.18323v1 Announce Type: new Abstract: Recent Omni-Modal Generative Models (Omni-Models) have advanced content generation toward unified modeling of text, images, video, and audio. MiniMax-H3
arXiv:2609.18131v1 Announce Type: cross Abstract: In this paper, we present a Mixture-of-Experts (MoE) quantization method based on activation entropy. Although quantization reduces memory and computa
arXiv:2609.17921v1 Announce Type: new Abstract: Vision-language model (VLM) agents combine specialized perception, tools, and reasoning to address complex visual tasks. In multi-agent settings, differ
arXiv:2503.12018v2 Announce Type: replace-cross Abstract: Text-to-Image (T2I) diffusion models have made rapid progress on semantic alignment (generating what is described in the prompt), yet users st
arXiv:2609.17883v1 Announce Type: cross Abstract: The rapid adoption of generative AI has made final artifacts unreliable evidence of student learning, and AI detectors that examine only the finished
arXiv:2609.17652v1 Announce Type: cross Abstract: When agentic sessions run to a million tokens with many sessions resident at once, the KV cache and the index that ranks it live in host memory, and t
arXiv:2609.19124v1 Announce Type: new Abstract: Emergent coordinated behaviors of AI agents are starting to present critical safety risks. A key phenomenon driving these behaviors is the rapid formati
arXiv:2609.18274v1 Announce Type: cross Abstract: Classroom observations are widely recognized as a key tool for establishing benchmarks of education quality and guiding pedagogical improvement, yet t
UPDATE https://github.com/ggml-org/llama.cpp/pull/29009 MERGED More Gen AI coverage and frameworks integrations to minimize code changes New models supported: On CPU: Gemma-3n On CPU, GPU: Kokoro-82M,
Epoch AI has launched “Benchmark Reviews,” an initiative to evaluate existing AI benchmark datasets. The program initially audits 15 benchmarks, categorizing them as 4 verified, 9 flawed, and 2 lackin
arXiv:2609.18317v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from a long-tail deficit: culturally specific facts, particularly those concerning underrepresented regions such a
arXiv:2412.07255v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) demonstrate remarkable capabilities in generative tasks but pose potential risks due to their tendency to generat
arXiv:2502.14254v3 Announce Type: replace-cross Abstract: Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have made them powerful tools in embodied navigation, en
arXiv:2609.17539v1 Announce Type: new Abstract: We present MudawanSn, a gold-standard resource of 1,271 sentence-aligned pairs manually translated from Wolof into Modern Standard Arabic (MSA). The sou
arXiv:2609.17890v1 Announce Type: new Abstract: Large reasoning models (LRMs) generate long chain-of-thought traces before answering, creating significant inference overhead. Pruning can reduce this c
Perhaps the most important warning I ever issued was this, to the US Senate, May 2023: “A month after GPT-4 was released, OpenAI released ChatGPT plug-ins, which quickly led others to develop somethin
arXiv:2609.19113v1 Announce Type: new Abstract: We evaluate six frontier language models on the two-agent log(N)-Questions game. A questioner sees N Wikipedia lead paragraphs and must identify a secre
arXiv:2609.18602v1 Announce Type: new Abstract: Despite recent progress in learned image compression, existing methods remain computationally expensive on resource-constrained hardware, particularly C
arXiv:2609.18262v1 Announce Type: new Abstract: Precise retrieval of scientific information is fundamentally constrained by long-tailed concepts and high fact-sensitivity of scientific corpora. These
arXiv:2609.17985v1 Announce Type: new Abstract: AI agents are usually evaluated by whether they complete a task. In interactive service settings, a successful agent can still frustrate users by asking
arXiv:2609.18672v1 Announce Type: new Abstract: An AI assistant that calls tools makes two decisions on every request: which tool to invoke, and whether any available tool applies. In the usual design
arXiv:2609.17855v1 Announce Type: new Abstract: Standardizing clinical language to SNOMED CT supports interoperability, analytics, and reusable phenotyping, but concept recommendation remains difficul