Knowledge catalogue
arXiv:2607.22334v1 Announce Type: cross Abstract: Open-weight language models from different families exhibit complementary capabilities, motivating their consolidation into a compact student through
arXiv:2607.22016v1 Announce Type: new Abstract: MEMEs are widely used on the internet and often carry strong elements of sarcasm or irony. Understanding their hidden meanings typically requires a join
arXiv:2607.21660v1 Announce Type: cross Abstract: Artificial intelligence (AI) is accelerating materials prediction and design by enabling efficient exploration of chemical and structural spaces, with
arXiv:2607.22456v1 Announce Type: new Abstract: Existing lexical distance, similarity, and evaluation metrics operate on Unicode code points, which can misrepresent errors in writing systems where a s
tldr; we are going to host K3 on A100s (yes, thats correct, we'll try to see if it holds up), H200s & B300s - expect results for A100s & H200s this week while we setup the B300 cluster this weekend &
arXiv:2508.05618v2 Announce Type: replace Abstract: Reasoning Large Language Models (R-LLMs) have significantly advanced complex reasoning tasks but often struggle with factuality, generating substant
arXiv:2607.22381v1 Announce Type: new Abstract: Curvature notions on graphs, particularly Ollivier-Ricci and Forman, have emerged as powerful tools for addressing fundamental issues in Graph Neural Ne
I've been building Krasis, an MoE-focused runtime for streaming big models through limited VRAM on NVIDIA consumer/workstation GPUs, and I think this is the most interesting result so far: Ornith-1.0-
arXiv:2607.21973v1 Announce Type: new Abstract: Vision foundation models are increasingly reused as frozen backbones for downstream visual recognition, making parameter-efficient adaptation a central
arXiv:2505.19212v2 Announce Type: replace Abstract: Recent advances in LLMs have enabled their use in complex agentic roles, involving decision-making with humans or other agents, making ethical align
Announcing the Claude Code-compatible interface for our new Fugu-Ultra v1.1! 🐡 Put a dynamically coordinated team of frontier models to work inside the coding workflow you already know. Instead of rel
Yes, open-source / open-weight models are important for a healthy AI ecosystem. That's how we can verify things, check claims, and keep up outside the closed labs. Plus, it gives us the freedom to run
Everything runs through WebGPU, in-browser or in electron/tauri apps. It's fully portable and supports either Nvidia and Apple Silicon (Metal). The actual kernels are optimized for the specific hardwa
I've spent the last year or so playing around with open source MLX and GGUF models on iPhone hardware. Given the limitations in memory, GPU/CPU/ANE, and in turn the context window I've been trying to
Quantized Krea 2 Turbo checkpoints for ComfyUI, up to 2x faster and about a third smaller than the usual FP8 version — no calibration dataset, no quality cliff. How to use it (short version): clone th
arXiv:2607.21057v1 Announce Type: new Abstract: Text-based person retrieval faces a critical but under-explored challenge: the inherent uncertainty of query granularity in real-world scenarios. This p
arXiv:2607.21482v1 Announce Type: new Abstract: Large language models (LLMs) and agents are now widely used tools in code development, with data typically sent to third-party cloud-based models. Their
arXiv:2607.21292v1 Announce Type: new Abstract: We present a structured large-language-model-driven workflow for automated multi-variable control design from dynamic process models. The workflow decom
arXiv:2607.21173v1 Announce Type: new Abstract: While automated research systems promise to accelerate empirical analysis, they are prone to silent failures: instances in which analysis code executes
arXiv:2607.20981v1 Announce Type: new Abstract: Efficient multimodal inference is increasingly constrained not only by model quality or FLOP count, but also by the cost of preserving, moving, routing,
I’m not affiliated with this project, but I’ve been running it recently and I’m surprised it hasn’t received more attention here: https://github.com/fewtarius/CachyLLama CachyLLama is a fork of llama.
arXiv:2607.20458v1 Announce Type: cross Abstract: Large language model (LLM) agents operating over extended dialogues accumulate vast amounts of information, yet existing memory systems either retain
arXiv:2607.21340v1 Announce Type: new Abstract: In capital-markets workflows the question is rarely whether a large language model can produce a fluent draft, but whether the draft is bankable: defens
arXiv:2607.20560v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems retrieve and integrate external knowledge to ground large language model (LLM) outputs. However, current RA
arXiv:2607.20526v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in settings where fluent but incorrect answers can be costly. In these settings, accuracy alone i
arXiv:2607.20630v1 Announce Type: cross Abstract: Traditional query processing engines require continuous development and extensions to support new techniques and user requirements, and in some cases,
arXiv:2607.20889v1 Announce Type: new Abstract: Editable 3D scene creation requires object instances and lights that can be inspected, moved, and imported into standard engines, yet existing single-im
arXiv:2607.21007v1 Announce Type: new Abstract: Deepfake detection is moving beyond binary classification decisions toward systems that can also explain the visual evidence supporting those decisions.
arXiv:2607.20946v1 Announce Type: new Abstract: Grievance is one of the warning signs analysts look for when assessing threats of violence. It is increasingly measured at scale from online text, most
arXiv:2607.20730v1 Announce Type: cross Abstract: Large language models increasingly use search tools to retrieve up-to-date information, introducing a new attack surface in which retrieved documents
arXiv:2607.21448v1 Announce Type: new Abstract: Dynamic scene reconstruction with 3D Gaussian Splatting requires a balance between fine-grained motion modeling, structural stability, and compact repre
arXiv:2607.20982v1 Announce Type: new Abstract: As large language model agents increasingly operate autonomously with access to tools and external environments, ensuring their safe and reliable behavi
arXiv:2607.21105v1 Announce Type: new Abstract: Although Multimodal Large Language Models have achieved strong performance across a wide range of vision-language tasks, they still suffer from hallucin
arXiv:2606.17028v2 Announce Type: replace-cross Abstract: Simple linear and frequency-domain models remain surprisingly competitive in long-horizon time-series forecasting, and recent mechanistic evid
arXiv:2607.20988v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models augmented with world modeling represent a promising paradigm for end-to-end autonomous driving. While pixel-level
arXiv:2607.21217v1 Announce Type: new Abstract: The recent emergence of vibe-coding workflows is changing what coding agents are expected to do. Instead of merely completing code under fully specified
arXiv:2607.20460v1 Announce Type: cross Abstract: Current full-duplex (FD) spoken dialogue systems can produce fluid interactions, yet it remains unclear whether they can adapt their turn-taking behav
arXiv:2603.20509v2 Announce Type: replace Abstract: Camera traps are vital for large-scale biodiversity monitoring, yet accurate automated analysis remains challenging due to diverse deployment enviro
arXiv:2604.00004v2 Announce Type: replace-cross Abstract: The extension of context windows in Large Language Models is typically facilitated by scaling positional encodings followed by lightweight Con
arXiv:2607.21384v1 Announce Type: new Abstract: Electroencephalography (EEG) models used for epilepsy are often limited to specific datasets and tasks. This limited approach can make it challenging to
arXiv:2607.21557v1 Announce Type: new Abstract: Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to e
arXiv:2607.20918v1 Announce Type: new Abstract: Omni-modal models can handle text, images, and audio in one system, but improving all of these abilities together remains difficult. Training a single m
Opus 5 is a great model for coding, data analysis, design, biology, knowledge work. More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt inject
arXiv:2607.09999v2 Announce Type: replace Abstract: We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved. Using a six-catego
arXiv:2607.15557v4 Announce Type: replace Abstract: Agent skills, SKILL files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Pub
arXiv:2607.21118v1 Announce Type: new Abstract: This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image resto
arXiv:2601.06487v3 Announce Type: replace-cross Abstract: Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on o
arXiv:2607.19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into
arXiv:2607.20225v1 Announce Type: cross Abstract: While combinatorial optimization problems are central to many scientific and engineering applications, their solution remains challenging due to expon
arXiv:2607.18688v1 Announce Type: new Abstract: Visible-Infrared Person Re-Identification (VI-ReID) operates under a closed-world assumption, where queries and galleries are from heterogeneous modalit
arXiv:2607.19375v1 Announce Type: cross Abstract: Language models perform economically valuable work, yet they are not currently assessed for how well they perform every economically valuable task. We
arXiv:2607.19947v1 Announce Type: new Abstract: Electronic Theater Programs (ETPs) serve as critical promotional media in the performing arts, comprising a multi-page collection of heterogeneous visua
arXiv:2607.09530v2 Announce Type: replace Abstract: We introduce Freya-TTS, a compact, tokenizer-free, Turkish-first text-to-speech model designed for highly reliable and efficient conversational synt
arXiv:2607.19111v1 Announce Type: new Abstract: Large pretrained vision models have substantially improved appearance-based 3D shape retrieval, but they still confuse shapes that look similar while di
arXiv:2512.24592v3 Announce Type: replace Abstract: Systematic failures of vision models on semantically coherent subsets, known as error slices, reveal limitations in robustness and evaluation. Exist
arXiv:2607.19999v1 Announce Type: new Abstract: This Good Practice Guide presents work done in the QUMPHY project (Uncertainty quantification for machine learning models applied to photoplethysmograph
arXiv:2607.19506v1 Announce Type: cross Abstract: Quantum reservoir computing (QRC) uses fixed quantum dynamics as a high-dimensional temporal feature map and trains only a lightweight classical reado
arXiv:2607.19324v1 Announce Type: new Abstract: In image and video technologies, data augmentation is widely used to improve the generalization of deep visual models, and mixup-based strategies that i
arXiv:2607.19837v1 Announce Type: new Abstract: Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that A
arXiv:2607.19399v1 Announce Type: cross Abstract: It is commonly observed that online reinforcement learning (RL) produces better-performing strategies than offline methods across a broad range of per