Knowledge catalogue
arXiv:2601.06953v3 Announce Type: replace Abstract: Competitive programming remains challenging for code LLMs. Despite recent progress, many training pipelines still depend on scarce real-world data,
arXiv:2603.17304v2 Announce Type: replace Abstract: Deep learning has become an important tool for Alzheimer's disease (AD) classification from structural MRI. Many existing studies analyze individual
arXiv:2608.28578v1 Announce Type: cross Abstract: Tendon-driven hands are anthropomorphic, and moving the actuators off the joints is what makes a hand of this capability affordable to build. Two effe
arXiv:2608.27477v1 Announce Type: cross Abstract: Graphical user interfaces have emerged as an important environment for evaluating autonomous AI agents on multimodal interactive tasks. Existing bench
arXiv:2506.04970v2 Announce Type: replace Abstract: Information on trees at the individual level is crucial for monitoring forest ecosystems and planning forest management. Current monitoring methods
I haven't had a chance to test it yet, but it looks very promising. It seems to speed up MTP for MoE models across different draft widths (especially greater than 1). Check the benchmarks. submitted b
arXiv:2608.28108v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs) allow users to specify manipulation tasks in natural language, but distinguishing a target or placement goal amon
arXiv:2608.28096v1 Announce Type: new Abstract: Learning-based image-to-point-cloud (I2P) registration has garnered increasing attention in recent years. Nevertheless, existing methods still struggle
arXiv:2608.27763v1 Announce Type: cross Abstract: Recurrent fast-weight memories and selective state-space models compress an expanding context into a fixed-size recurrent state, making the state tran
glm-5.3 now beats gpt-5.6 sol and claude fable 5 on agentic benchmarks 5.3 flash is right behind it glm-5.3 didn’t even need a new base model to get there @zai_org kept the glm-5.2 base and scaled pos
arXiv:2608.27760v1 Announce Type: new Abstract: We consider the ability of transformer-based language models (LLMs) to learn what we call k-antilocal languages, i.e., languages that have no mutual inf
Interesting paper from Tencent. Tencent trains an agent to manage its own working context, and assigns credit at the level of individual context edits. Long-horizon tasks force a model to retrieve, in
arXiv:2608.28174v1 Announce Type: new Abstract: Video re-shooting re-renders a monocular video of a dynamic scene along a user-specified camera trajectory, and the dominant recipe supplies the target
arXiv:2608.28379v1 Announce Type: cross Abstract: Quantum federated learning enables collaborative model training across quantum devices without sharing raw data, and it faces the data and hardware he
Mac Studio, 96GB unified memory (M3 Ultra). I want the largest usable Qwen3.8-Flash-Next setup, and I'd rather not burn 100GB of bandwidth on the wrong download. Here's my math. Please tell me which p
arXiv:2608.28366v1 Announce Type: cross Abstract: State estimation in magnetohydrodynamic flows is critical for real-time monitoring of liquid metal blankets in tokamak fusion reactors. Due to the mul
arXiv:2606.16113v2 Announce Type: replace-cross Abstract: Algorithmic recourse methods provide counterfactual explanations that inform individuals of the actions required to overturn an unfavorable mo
arXiv:2510.25384v2 Announce Type: replace Abstract: Large Language Models (LLMs) are promising tools for synthetic data generation in mental health. However, privacy policies and restrictions forced p
→ rollout throughput: generation speed and GPU utilization → weight sync: fresh weights on the rollout deployment every step → correctness: trainer and inference engine agreeing on the same model Cofo
arXiv:2608.27783v1 Announce Type: cross Abstract: Speech LLMs are usually graded after they answer, although an operating system first has to decide whether a waveform should be sent to the model. We
arXiv:2608.28408v1 Announce Type: new Abstract: Tabular data, as a core data format in machine learning, often lacks the discriminative power needed for high-performance modeling due to insufficient f
arXiv:2608.27931v1 Announce Type: new Abstract: This study proposes a novel framework to estimate parameters for reproducing target multicellular patterns using an agent-based model (ABM). Two major c
dflash: pass missing NVFP4 scales to attention operations (#28000) DFlash2 NVFP4 draft models produced almost no accepted speculative tokens because the Q, K, V, and output projection scales were not
I'm running Muse Glimmer 30B EXL3-SC 3.00bpw H4, fully resident on my 12GB VRAM GPU at 100K context with Q8_O KV cache. It's a joy to use a dense 30B model at this size and still get 30 tok/s on a VRA
I am doing a lot of translation work with different languages, and German is just exceptionally well done by Qwen 3.8 27B. It is lengths ahead of GPT-5.6 and even Fable 5. With the frontier models I o
// Your LLM judge disagrees with the experts // LLM Judges can be tricky to build. Here is an interesting showcasing why: There propose a reference-full benchmark of hundreds of complete human-to-huma
// Memory is what breaks long-horizon agents // It's undeniable how important memory/recall is for long-horizon tasks. If you are building for long-horizon tasks, this is a great read. (bookmark it) T
Hey! I forked NInfer (a from-scratch C++20/CUDA inference engine for Qwen models) and added two things: tensor-parallel across two GPUs, and YaRN ×4 rope scaling. Together they let Qwen3.8-27B NVFP4 r
I ran a few benchmarks on my MacBook Pro M5 Max with oMLX: Running Qwen3.8-27B with thinking off has a big effect on output quality. Running it with thinking on xhigh burns 5.5x the tokens and runs 6x
Qwen 125B/6B models with a 1‑million‑token context window and multimodal support have been released on Alibaba’s OpenCode Go platform. The new Qwen3.8‑Flash variant is also now available in the same e
arXiv:2608.26234v1 Announce Type: cross Abstract: Retail electricity markets in deregulated systems face significant price volatility and complex interactions with forward and futures products, posing
arXiv:2608.26363v1 Announce Type: new Abstract: This paper introduces a unified mathematical framework for modeling information propagation through convolutional neural networks (CNNs), with the aim o
arXiv:2608.27080v1 Announce Type: cross Abstract: Many scientific and engineering applications require estimating unknown parameters from experimentally observable data -- an inverse problem that is i
arXiv:2608.26434v1 Announce Type: new Abstract: Code-switching is pervasive in bilingual African conversation, yet most ASR systems assume monolingual input and are evaluated on curated monolingual be
arXiv:2608.26198v1 Announce Type: new Abstract: Operating a scientific instrument such as an atomic force microscope (AFM) requires continuous expert decision-making. A trained user defines the experi
arXiv:2608.27169v1 Announce Type: new Abstract: Ancient Chinese artifact text recognition is fundamental to heritage digitization, and benchmarks for ancient texts are essential for evaluating current
Anthropic PBC today previewed a standard that makes it easier for artificial intelligence agents to control machines such as microscopes. The Model Hardware Standard, or MHS, is the fruit of a collabo
arXiv:2608.26993v1 Announce Type: new Abstract: Explicit visual intermediates can help multimodal large language models (MLLMs) externalize spatial evidence and updated visual states, but their utilit
arXiv:2608.26306v1 Announce Type: new Abstract: A large language model (LLM) guardrail for a self-adaptive system (SAS) may issue an approval that is correct at check time but stale by actuation. This
arXiv:2608.26213v1 Announce Type: cross Abstract: Large language model (LLM)-based audio-visual speech recognition (AVSR) systems are robust under noise. Contrastive decoding (CD), originally introduc
model: qwen4exp: reduce number of graph splits (#27880) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43734155 macOS/iOS: macOS Apple Silicon (arm64) macO
arXiv:2608.27219v1 Announce Type: new Abstract: Mental health assessment relies on episodic self-report scales, which convert subjective states such as stress into numerical scores but provide only sp
arXiv:2608.26332v1 Announce Type: new Abstract: Managed LLM services are now part of real production systems, but model selection and service planning still rely heavily on capability benchmarks that
arXiv:2608.27167v1 Announce Type: new Abstract: An LLM agent shown a professional-looking market panel commits to a directional call on a provably unpredictable question far more often than one asked
arXiv:2608.26114v1 Announce Type: new Abstract: Calculation-intensive financial question answering requires exact reasoning over structured rates, temporal conditions, numerical formulas, and rule-bas
arXiv:2608.27214v1 Announce Type: new Abstract: Open World Object Detection (OWOD) built on multimodal foundation models often suffers from semantic ambiguity caused by unidirectional text-to-vision m
arXiv:2505.08143v2 Announce Type: replace-cross Abstract: With the wide adoption of large language models (LLMs) in information assistance, it is essential to examine their alignment with human commun
arXiv:2608.26357v1 Announce Type: new Abstract: Large language models (LLMs) exhibit uneven multilingual performance, especially when dealing with low-resource languages. Inference-time intervention o
arXiv:2608.26129v1 Announce Type: cross Abstract: Scientific peer review datasets have trained AI systems exclusively on Computer Science and Machine Learning venues, producing models that critique ab
arXiv:2608.27029v1 Announce Type: cross Abstract: Training molecular machine-learning models on ephemeral or memory-constrained accelerator instances can require repeatedly retrieving preprocessed mol
arXiv:2608.26856v1 Announce Type: cross Abstract: Although Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in Medical Visual Question Answering (Med-VQA), their relia
Model: unsloth/GLM-5.3-Flash-GGUF UD-Q2_K_XL (4 shards, 101 GiB) + mmproj-BF16. Reference: llama.cpp PR #27754 (glm5next), CUDA 12.8, SM 120. Throughput Both engines back to back in one session, flash
arXiv:2608.26157v1 Announce Type: new Abstract: Natural-language analytics over enterprise data warehouses is increasingly important, but production use is limited by hallucinated metrics, invalid joi
arXiv:2608.26517v1 Announce Type: new Abstract: Visual intelligence seeks to perceive, interpret, and synthesize the visual world and is central to modern computer vision. Human-centered visual intell
However, I keep getting a 404 error when trying to access qwen3.8-flash-next:125b-mlx and ornith-1.5:397b via the API, even though they are listed in the model list. Does anyone know why this is happe
arXiv:2608.27348v1 Announce Type: new Abstract: As large language models (LLMs) are deployed as autonomous agents, safety failures increasingly involve consequential actions. We study agentic misalign
arXiv:2608.26186v1 Announce Type: cross Abstract: This study examines how prompt and response language influence the behavior of large language models. Using five models, we evaluated answers to 68 no
arXiv:2608.26982v1 Announce Type: new Abstract: Large language model (LLM) judges are increasingly used across various evaluation scenarios, making their judgment capabilities valuable intellectual pr
arXiv:2505.14104v2 Announce Type: replace Abstract: Legal rules encompass not only codified statutes but also implicit adjudicatory principles derived from precedents that contain discretionary norms,
arXiv:2608.26389v1 Announce Type: new Abstract: SVD-based low-rank compression has become a fast-growing direction for reducing the memory and computational cost of large language models (LLMs). Howev