Knowledge catalogue
arXiv:2608.24735v1 Announce Type: new Abstract: Self-improving LLM agents refine answers, not the process that produces those answers. Systems that add a meta-level hold that level fixed, and those th
arXiv:2608.24340v1 Announce Type: cross Abstract: The prediction of student engagement from the online tutoring videos is difficult because engagement is a multidimensional construct comprising distin
arXiv:2608.23761v1 Announce Type: cross Abstract: Highly overparameterized models often predict well despite interpolating training data in complex domains, challenging the classical bias--variance tr
arXiv:2608.24486v1 Announce Type: cross Abstract: Purpose: To quantify how evaluation annotations influence measured pulmonary embolism (PE) segmentation performance relative to model training changes
Hi, So I’m running Qwen on M4 Pro (ollama) and it drives me nuts at times. For example it’s trying to use grep with flags which don’t work on Mac. Or it’s writing some python code and failing and then
arXiv:2608.24783v1 Announce Type: new Abstract: Accurate segmentation of coronary arteries in X-ray angiography videos is essential for quantitative coronary analysis and image-guided interventions. H
arXiv:2608.23646v1 Announce Type: new Abstract: Molecular embedding models can serve as foundational infrastructure for computational chemistry and drug discovery, where reusable vector representation
arXiv:2608.23962v1 Announce Type: new Abstract: When an LLM serving deployment runs out of KVcache room, there are two well-established ways out. Tensor parallelism shards the weights and the KV cache
arXiv:2608.24531v1 Announce Type: cross Abstract: Probabilistic full-field reconstruction provides uncertainty-aware response evidence for structural reliability assessment, yet inference from sparse
Most users never rate a bad interaction. They just stop. Perceived Error is LangSmith's new managed judge that reads thread evidence and flags where your agent went sideways. Trained in-house, outperf
arXiv:2602.06268v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly integrated into clinical workflows. However, pr
arXiv:2608.24534v1 Announce Type: new Abstract: Clinical LLMs can generate recommendations that are factually plausible yet physiologically unsafe. We investigate whether safety alignment can be impro
No reward hacking was found in GLM-5.2: solve the task, not the benchmark. Introducing reward hacking score corrections to the Artificial Analysis Coding Agent Index In v1.4 of the Artificial Analysis
Now we know: The popular Ox Alpha LLM was GLM-5.3-Flash... Compared to GLM-5.2, this new GLM-5.3-Flash model uses: - a Kimi Linear-style 3:1 (super*) hybrid attention pattern with 34 Kimi Delta Attent
The next wave of AI is placing new demands on infrastructure. As AI agents and trillion-parameter workloads become mainstream, the performance of AI infrastructure depends not only on compute, but on
arXiv:2608.23845v1 Announce Type: new Abstract: Object-counting methods have rapidly shifted from class-specific density regression to open-vocabulary, foundation-model-backed counters. These methods
arXiv:2312.17535v2 Announce Type: replace Abstract: In the past two years, the outstanding performance of ChatGPT in multilingual and multitasking has led to large language models (LLMs) attracting wi
Ollama v0.33 has been released, adding support for easy integration with Claude Desktop. By toggling a setting, users can configure Claude to use Ollama as a third‑party gateway provider, enabling bot
arXiv:2608.24160v1 Announce Type: new Abstract: Multimodal understanding models that can jointly judge text-to-image (T2I), text-to-video (T2V) and text-to-speech (TTS) generation are increasingly use
On August 26, 2026 Z.ai reported that its Code‑Bench metric—which assesses real‑world coding performance—shows GLM‑5.3‑Flash outperforming GLM‑5.2 at every effort level. The new model’s results are on
So here's the thing, almost everyone use NVIDIA to run their LLMs, we also do the same, a lot of people we've met use like RTX PRO 6000 or even H100, B300 It seems like everyone eyes is looking at NVI
In the past, I have use llama.cpp, but I read that the exl3 quantization format should give better precision, so I have tried exllamav3/tabbyAPI. It was able to write the shown simple HTML game withou
arXiv:2608.24073v1 Announce Type: cross Abstract: Low-earth-orbit (LEO) satellites enable high-resolution, large-scale Earth observation for applications such as disaster monitoring and environmental
arXiv:2608.24727v1 Announce Type: cross Abstract: EEG foundation models pretrained via self-supervised learning promise transferable representations, but their generalization remains limited, especial
arXiv:2608.24700v1 Announce Type: new Abstract: When a network has learned a function with a known symmetry, can that symmetry be moved through the parametrisation---is there a motion in parameter spa
arXiv:2608.24865v1 Announce Type: cross Abstract: Lipschitz constants are a standard way to quantify the sensitivity of neural networks to small input perturbations, but computing them is difficult ev
arXiv:2608.24658v1 Announce Type: new Abstract: Scaling test-time reasoning has substantially improved the problem-solving ability of large language models (LLMs), but standard autoregressive decoding
arXiv:2608.24188v1 Announce Type: new Abstract: Coding agents re-send large file reads and tool outputs to a frontier LLM every turn, and this context dominates their token bill. General-purpose promp
arXiv:2608.24509v1 Announce Type: new Abstract: LLM agents increasingly solve tasks by invoking multiple tools, where parallel execution is essential for low latency but difficult to manage safely. Ex
arXiv:2608.24049v1 Announce Type: new Abstract: Neural operators provide efficient surrogates for spatiotemporal PDE systems, but purely data-driven formulations often accumulate substantial errors du
arXiv:2608.24056v1 Announce Type: new Abstract: Generative and predictive artificial intelligence models are increasingly used to generate geometry and to predict physical fields and scalar quantities
arXiv:2608.23841v1 Announce Type: cross Abstract: Single-token autoregressive decode on CPUs is bound by memory bandwidth, not arithmetic: a modern CPU sustains roughly 1 TFLOP/s of compute but only a
arXiv:2608.24585v1 Announce Type: new Abstract: Automated high-density storage systems (warehouses, robotic parking, plant logistics, etc.) require fleets of agents to move through scarce task-critica
arXiv:2608.24192v1 Announce Type: new Abstract: Aligning large language models to human preferences is crucial for real-world deployment but frequently incurs an alignment tax, leading to the catastro
arXiv:2608.23911v1 Announce Type: new Abstract: Supervised fine-tuning on teacher-generated trajectories is the standard first stage for distilling tool-calling capabilities into deployable models. Po
arXiv:2608.23893v1 Announce Type: new Abstract: Learning systems deployed over long periods must adapt not only to statistical changes in incoming data, but also to revisions of the definitions that g
arXiv:2608.23843v1 Announce Type: new Abstract: Long-context inference in large language models (LLMs) is increasingly limited by the memory required for the key-value (KV) cache. KV cache compression
arXiv:2411.15209v3 Announce Type: replace Abstract: The expansion of time-series data from sensors and monitoring systems has made compact representations increasingly important. Such representations
arXiv:2602.00704v2 Announce Type: replace Abstract: The generation of Register-Transfer Level (RTL) code is a crucial yet labor-intensive step in digital hardware design, traditionally requiring engin
arXiv:2608.23934v1 Announce Type: cross Abstract: Nitrogen-vacancy (NV) centers in diamond can serve as highly sensitive solid-state quantum sensors for high-sensitivity magnetometry. However, in the
https://preview.redd.it/i8rjx0ar5mlh1.png?width=2160&format=png&auto=webp&s=c2588bc7b2519ea71b176ca73faf566dfc585496 I wanted to see whether a heavily quantized 27B model running entirely on an older
Qwen3.8-Flash-Next Another open weights model from Qwen. This one is 'a multimodal MoE model that also serves as an early preview of the architecture used in Qwen4'. It's pretty big: 125B tokens, but
arXiv:2608.23965v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves the factuality of large language models by grounding responses in external documents, but it also expose
arXiv:2608.23956v1 Announce Type: new Abstract: Test-time reasoning methods such as iterative refinement, decomposition, and repeated sampling are often evaluated in isolation, making their gains diff
arXiv:2608.24876v1 Announce Type: new Abstract: Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We in
arXiv:2608.23611v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer new opportunities for automated code refactoring. However, generated changes must reduce targeted quality problems
arXiv:2608.24041v1 Announce Type: new Abstract: Although Speech Large Language Models (SpeechLLMs) excel at speech understanding and generation, their capacity for fine-grained, temporally aligned out
arXiv:2608.23568v1 Announce Type: new Abstract: Memory and RAG evaluations often treat the answering model's input as an implementation detail, even though systems may render the same history as a mem
arXiv:2608.24291v1 Announce Type: new Abstract: Paper-to-code reproduction asks scientific AI agents to turn research papers into executable repositories that preserve the paper's method, protocol and
arXiv:2608.23725v1 Announce Type: new Abstract: Deep Equilibrium Models (DEQs) compute predictions from a hidden representation unchanged by the model update. Training through this equilibrium uses im
arXiv:2608.23799v1 Announce Type: cross Abstract: Recent progress in image restoration has converged on all-in-one architectures that jointly handle multiple degradations within a single network. Thes
arXiv:2608.23860v1 Announce Type: cross Abstract: Revelation Control is the problem of choosing priced interventions that reveal hidden state only insofar as the revealed distinctions can change a con
arXiv:2608.24135v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) has emerged as a pivotal technique for enhancing the code generation capabilities of Large Languag
arXiv:2512.12703v2 Announce Type: replace-cross Abstract: Extracting human motion from large-scale web videos offers a scalable solution to the data scarcity issue in character animation. However, som
arXiv:2608.24252v1 Announce Type: new Abstract: LLM agents can generate paper reproduction code, yet often produce scientifically unfaithful implementations. We define this failure mode as semantic dr
arXiv:2608.24011v1 Announce Type: cross Abstract: Chinese ancient document understanding demands complex visual, linguistic, and historical reasoning. Current Large Vision-Language Models (LVLMs) typi
Michael Nuñez / VentureBeat: Salesforce and Anthropic unveil Claudeforce, which brings Salesforce data and workflows into Claude, starting with a plugin featuring 37 prebuilt sales skills — Salesforce
arXiv:2608.24173v1 Announce Type: new Abstract: Quantization correction methods usually optimize weights, quantization parameters, or reconstruction objectives, while the underlying parameter subspace
arXiv:2608.24500v1 Announce Type: cross Abstract: The STAR (Student-Teacher Achievement Ratio) experiment (1985, Tennessee, USA) is a landmark hierarchical dataset designed to assess the impact of cla
arXiv:2602.19624v2 Announce Type: replace Abstract: Recent state-of-the-art visual trackers produce high quality and long-term-stable segmentation masks. We propose to leverage these strengths for pla