Knowledge catalogue
arXiv:2604.13630v1 Announce Type: cross Abstract: The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context
arXiv:2604.14168v1 Announce Type: new Abstract: We introduce SAGE Celer 2.6, the latest in our line of general-purpose Celer models from SAGEA. Celer 2.6 is available in 5B, 10B, and 27B parameter siz
arXiv:2604.07663v2 Announce Type: replace Abstract: The AdamW optimizer, while standard for LLM pretraining, is a critical memory bottleneck, consuming optimizer states equivalent to twice the model's
arXiv:2512.08914v2 Announce Type: replace-cross Abstract: Quantum Error Correction (QEC) decoding faces a fundamental accuracy-efficiency tradeoff. Classical methods like Minimum Weight Perfect Matchi
arXiv:2604.14862v1 Announce Type: new Abstract: Constrained decoding has been widely adopted for structured generation with large language models (LLMs), ensuring that outputs satisfy predefined forma
arXiv:2604.13474v1 Announce Type: cross Abstract: We propose a novel end-to-end privacy-preserving framework, instantiated by three efficient protocols for different deployment scenarios, covering bot
arXiv:2604.01473v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing g
Sharing my current setup to run Qwen3.6 locally in a good agentic setup (Pi + llama.cpp). Should give you a good overview of how good local agents are today: # Start llama.cpp server: llama-server -hf
arXiv:2604.14339v1 Announce Type: new Abstract: Large language models (LLMs) increasingly operate in settings that require reliable long-context understanding, such as retrieval-augmented generation a
arXiv:2604.14879v1 Announce Type: new Abstract: Nonlinear system identification must balance physical interpretability with model flexibility. Classical methods yield structured, control-relevant mode
SpaceX completed two Starlink launches about 19 hours apart, pushing the number of Starlink satellites launched in 2026 past 1,000. Starlink 10-24 from Florida put 29 V2 Mini satellites into orbit wit
arXiv:2603.16024v2 Announce Type: replace Abstract: We introduce a speech-guided embodied agent framework for video-guided skull base surgery that dynamically executes perception and image-guidance ta
Starting in v2.1.113, the Claude Code npm package ships the native binary instead of the JavaScript build. Same install command, faster startup, and the CLI no longer needs Node.js at runtime. If you
Real-time threat intelligence company Team Cymru Inc. today announced the launch of Total Insights Feed, a unified threat intelligence platform that is designed to replace legacy indicator list-based
arXiv:2509.15602v5 Announce Type: replace Abstract: Multimodal large language models (MLLMs) excel at general video understanding but struggle with fast, high-frequency sports like tennis, where rally
The Claude Code hackathon is back for Opus 4.7. Join builders from around the world for a week with the Claude Code team in the room, with a prize pool of $100K in API credits. Apply by Sunday: https:
arXiv:2604.14558v1 Announce Type: new Abstract: This paper presents the NTIRE 2026 image super-resolution (imes4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026.
This post announces Ornstein3.6-35B-A3B-GGU, a fine-tuned variant of Qwen 3.6 35B model available on Hugging Face, with the author claiming it represents a high-quality optimization of the base model.
arXiv:2603.11875v2 Announce Type: replace-cross Abstract: Prompt injection defenses are often framed as semantic understanding problems and delegated to increasingly large neural detectors. For the fi
arXiv:2507.02935v2 Announce Type: replace Abstract: Successful human-agent teaming relies on an agent being able to understand instructions given by a (human) principal. In many cases, an instruction
arXiv:2604.15301v1 Announce Type: new Abstract: Many SLT systems quietly assume that brief chunks of signing map directly to spoken-language words. That assumption breaks down because signers often cr
arXiv:2604.14430v1 Announce Type: new Abstract: We present Three-Phase Transformer (3PT), a residual-stream structural prior for decoder-only Transformers on a standard SwiGLU + RMSNorm + RoPE + GQA b
arXiv:2507.15066v5 Announce Type: replace Abstract: Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lacks the fine-grained categorization and explanat
arXiv:2510.25892v2 Announce Type: replace Abstract: We propose a graph-topological approach to active learning that directly targets the core challenge of exploration versus exploitation under scarce
arXiv:2507.23121v2 Announce Type: replace Abstract: In this work, we study a critical research problem regarding the trustworthiness of large language models (LLMs): how LLMs behave when encountering
arXiv:2604.14550v1 Announce Type: cross Abstract: Generating synthesizable Verilog for large, hierarchical hardware designs remains a significant challenge for large language models (LLMs), which stru
arXiv:2512.18436v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown impressive capability to understand and develop code. However, their capability to rigorously reason a
arXiv:2505.20291v4 Announce Type: replace-cross Abstract: Text-to-image retrieval (T2I retrieval) remains challenging because cross-modal embeddings often behave as bags of concepts, underrepresenting
We need a new document that AI labs should release with each new model, besides the model card: a sort of changelog I want to see how & in what way the new model changes, breaks, or improves at a rang
arXiv:2604.13694v1 Announce Type: new Abstract: Mechanistic interpretability seeks to localize model behavior to the internal components that causally realize it. Prior work has advanced activation-sp
We’re adding more visibility into where your Claude Code usage goes. Run /usage to see a breakdown of what's driving it: parallel sessions, subagents, cache misses, long context, plus tips to optimize
What a week! Here’s everything we shipped: — Gemini 3.1 Flash TTS, our latest text-to-speech model, featuring native multi-speaker dialogue and improved controllability and audio tags for more natural
What folk don’t get is that the play of Anthropic et al is to get enterprises to use their models via their own wrapper hooked into systems of record This is why they are moving from per seat pricing
arXiv:2604.15010v1 Announce Type: cross Abstract: When do transformers commit to a decision, and what prevents them from correcting it? We introduce extbf{prolepsis}: a transformer commits early, task
arXiv:2604.15167v1 Announce Type: new Abstract: Post-training quantization (PTQ) assumes that a well-converged model is a quantization-ready model. We show this assumption fails in a structured, measu
arXiv:2604.14356v1 Announce Type: new Abstract: Women with polycystic ovary syndrome (PCOS) face substantially elevated risks of body image distress, disordered eating, and metabolic challenges, yet e
arXiv:2604.14540v1 Announce Type: new Abstract: Detecting slow-moving landslides directly from wrapped Interferometric Synthetic Aperture Radar (InSAR) interferograms is crucial for efficient geohazar
🇺🇸 xAI just dropped a real-time speech-to-text model built for voice apps: high limits, multi-language support, the works. Priced at just 0.10–0.20/hour, crushing most competitors. Quiet release, loud
arXiv:2604.14883v1 Announce Type: new Abstract: Recent advances in Deep Learning (DL) have strengthened data-driven System Identification (SysID), with Neural and Fuzzy Ordinary Differential Equation
arXiv:2604.14880v1 Announce Type: new Abstract: Recent advances in Deep Learning (DL) have boosted data-driven System Identification (SysID), but reliable use requires Uncertainty Quantification (UQ)
arXiv:2604.14934v1 Announce Type: new Abstract: Automatic evaluation metrics are essential for building multilingual translation systems. The common practice of evaluating these systems is averaging m
arXiv:2604.14846v1 Announce Type: new Abstract: Retail theft costs the global economy over 100 billion annually, yet existing AI-based detection systems require expensive custom model training on prop
180 tok/s generation on a 4090 with qwen 3.6. if you're on a 4090 and not running this model yet you're leaving performance on the table. 3B active params at that speed is insane for agentic coding. t
arXiv:2604.13244v1 Announce Type: new Abstract: The 4th Workshop on Maritime Computer Vision (MaCVi) is organized as part of CVPR 2026. This edition features five benchmark challenges with emphasis on
6/ Give Claude a way to verify its work Finally, make sure Claude has a way to verify its work. This has always been a way to 2-3x what you get out of Claude, and with 4.7 it's more important than eve
arXiv:2604.14059v1 Announce Type: cross Abstract: This paper provides a systematic comparison between Fitted Dynamic Programming (DP), where demand is estimated from data, and Reinforcement Learning (
arXiv:2604.14037v1 Announce Type: new Abstract: Parameter space is not function space for neural network architectures. This fact, investigated as early as the 1990s under terms such as ``reverse engi
arXiv:2604.13763v1 Announce Type: cross Abstract: To date, various paradigms of soft-Computing have been used to solve many modern problems. Among them, a self organizing combination of fuzzy systems
arXiv:2501.02378v2 Announce Type: replace Abstract: Abrupt learning is a common phenomenon in recurrent neural networks (RNNs) trained on working memory tasks. In such cases, the networks develop tran
A https://claude.ai/ feature I really like is you can tell it to 'clone x/y from GitHub' and it can then answer questions about a repo, or use snippets of code from that repo to help build new artifac
arXiv:2604.13112v1 Announce Type: new Abstract: Reliable image quality assessment is essential in applications where large volumes of images are acquired automatically and must be filtered before furt
A lot of papers coming out are still focused on GPT-4, but you could extrapolate their effects to GPT-5, etc. Much harder to know what the impacts of Claude Code/Codex etc. are because they are so new
arXiv:2604.13059v1 Announce Type: new Abstract: Most dialogue-based electronic medical record (EMR) systems still behave as passive pipelines: transcribe speech, extract information, and generate the
a quick fix if you saw higher rate limit usage in Opus 4.7 today- hope you enjoy trying it out We fixed a bug where rate limits on Claude subscriptions weren't properly adjusted for long context reque
arXiv:2604.13448v1 Announce Type: new Abstract: Human-object interaction (HOI) detection aims to detect interactions between humans and objects in images. While recent advances have improved performan
OpenAI discusses efforts to strengthen collective cybersecurity defenses through collaboration and technology advancement within the broader cyber defense ecosystem. The article likely covers OpenAI's
arXiv:2602.16385v4 Announce Type: replace Abstract: Independent indoor mobility remains a critical challenge for individuals with visual impairments, largely due to the limited capability of existing
arXiv:2512.08639v3 Announce Type: replace Abstract: Aerial Vision-and-Language Navigation (VLN) aims to enable unmanned aerial vehicles (UAVs) to interpret natural language instructions and navigate c
arXiv:2604.13369v1 Announce Type: cross Abstract: Surrogate modeling of body-driven fluid flows where immersed moving boundaries couple structural dynamics to chaotic, unsteady fluid phenomena remains
Agent evals are drifting away from production reality. Most benchmarks use clean tasks, well-specified requirements, deterministic metrics, and retrospective curation. Production work is messier, with