b10750
kv-cells: look up the n-gram history in the sequence position index (#28040) get_prev_tokens() rebuilt a (seq, pos) -> token hash map on every ubatch by walking all used cells, while llama_kv_cells al
Knowledge catalogue
kv-cells: look up the n-gram history in the sequence position index (#28040) get_prev_tokens() rebuilt a (seq, pos) -> token hash map on every ubatch by walking all used cells, while llama_kv_cells al
cuda: fuse MoE weighted expert reduction (#25952) cuda : fuse MoE weighted reduction (mul + view + add) The MoE combine tail currently writes weighted expert outputs to global memory before reducing t
arXiv:2608.29196v1 Announce Type: new Abstract: Optic disc (OD) segmentation is essential for diagnosing ophthalmic pathologies from retinal fundus images. However, prevailing deep learning approaches
arXiv:2608.30536v1 Announce Type: new Abstract: Reliable execution of long-horizon mobile manipulation tasks remains challenging because overall task success depends on the successful completion of mu
arXiv:2608.29428v1 Announce Type: new Abstract: Single-trial EEG analyses are often organized around events and latencies, yet EEG-based reaction-time (RT) prediction is posed as scalar regression on
arXiv:2608.29206v1 Announce Type: new Abstract: Bias in human-agent interaction can manifest not only through hostile language but also as benevolent bias, whereby unequal treatment hides behind a war
arXiv:2606.15932v3 Announce Type: replace Abstract: While Large Language Models (LLMs) have substantially advanced text-to-code generation, many real programming tasks specify intent through visual ar
arXiv:2608.30686v1 Announce Type: cross Abstract: Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity can
arXiv:2608.30035v1 Announce Type: new Abstract: Self-evolving reasoning frameworks train a Challenger to generate questions exposing a Solver's weaknesses, creating adaptive curricula without human da
arXiv:2608.29658v1 Announce Type: cross Abstract: Accurate traffic flow prediction is fundamental to intelligent transportation systems, playing a pivotal role in urban mobility optimization and smart
arXiv:2608.30689v1 Announce Type: new Abstract: Autoregressive large models have recently advanced Text-to-SVG generation from simple icons to complex, long-context graphics, yet standard autoregressi
arXiv:2608.28681v1 Announce Type: new Abstract: Probability calibration aligns model confidence with predictive accuracy, enabling clinicians to identify unreliable segmentation regions. This alignmen
Information technology services company CBTS Technology Solutions LLC today launched Forge Agents, a platform that turns a plain-language description of a job into a working artificial intelligence ag
arXiv:2608.30498v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable success in STEM domains, where progress is often driven by vertical, step-by-step deducti
arXiv:2608.28909v1 Announce Type: new Abstract: Large-scale, publicly available datasets have driven advances in deep learning, but privacy and legal restrictions often limit data sharing in medical i
arXiv:2608.29223v1 Announce Type: new Abstract: Accurate through-thickness measurement of subsurface delamination depth in Carbon Fiber Reinforced Polymer (CFRP) is important for structural assessment
arXiv:2608.30183v1 Announce Type: cross Abstract: Lightweight channel attention mechanisms are widely used in image classification, yet their effectiveness in fine-grained visual recognition (FGVR) re
arXiv:2608.30792v1 Announce Type: cross Abstract: Obtaining data from neuromorphic sensors and processing it with Spiking Neural Networks is a promising solution to lower the energy cost of artificial
arXiv:2602.05863v3 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) remains the dominant critic-free approach for fine-tuning LLMs and VLMs, but its compatibility with
arXiv:2608.29920v1 Announce Type: new Abstract: Test-time adaptation (TTA) promises robustness under distribution shift by updating a pretrained model on unlabeled test data, but strict online TTA wit
arXiv:2608.30382v1 Announce Type: new Abstract: Popular adaptive stochastic gradient descent (SGD) methods to train artificial intelligence (AI) systems include the RMSprop, the Adam, and the AdamW op
arXiv:2608.30768v1 Announce Type: new Abstract: Automatic neuron reconstruction from light microscopy images is a central problem in computational neuroanatomy. While recent methods have achieved enco
CrowdStrike Holdings Inc. today unveiled Falcon Guardian, software that finds the artificial intelligence agents running inside a company and shuts down the ones security teams have not approved. The
arXiv:2608.29966v1 Announce Type: new Abstract: Domain adaptation of large language models increasingly depends on constructing high-quality training data, yet existing data-preparation pipelines typi
arXiv:2502.10673v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has become an effective method for enhancing large language models (LLMs) with up-to-date knowledge. Howe
arXiv:2608.29465v1 Announce Type: cross Abstract: Deployed decisions are often optimized once and retained because updates impose operational, regulatory, or switching costs. As operating conditions c
arXiv:2608.30023v1 Announce Type: cross Abstract: Generative engines such as ChatGPT, Gemini, and Perplexity answer buyer questions directly and name a shortlist of brands inside the answer. Studying
arXiv:2608.28824v1 Announce Type: new Abstract: Currently, in biological systems Neural Correlates of Consciousness (NCCs) are characterized in terms of EEG and FMRI signals. Unfortunately, this chara
arXiv:2608.29078v1 Announce Type: new Abstract: Vision-language-action (VLA) models have made strong progress in language-conditioned robot manipulation, but improving their performance in a new works
arXiv:2608.31106v1 Announce Type: new Abstract: Recent video generators often omit audio or synthesize it in a separate stage, limiting reciprocal modeling of visual dynamics and acoustic events. We p
arXiv:2601.16690v2 Announce Type: replace Abstract: We introduce EMemBench, a programmatic benchmark generator for evaluating long-term episodic memory of agents through interactive games. Rather than
arXiv:2608.30446v1 Announce Type: cross Abstract: Small-cap-inclusive equity universes contain recently listed and intermittently traded securities, so enforcing a common look-back discards a substant
arXiv:2507.00754v3 Announce Type: replace Abstract: The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the
arXiv:2608.29264v1 Announce Type: new Abstract: Diffusion-based visual generative models deliver strong image and video synthesis quality but incur high inference costs because sequential samplers rep
More new massive updates from turboderp: - CPU offload of MoE experts - Qwen-3.8-Flash-Next ngram disk offload - GLM-5.3-Flash - New self-calibrated optimization technique - Countless other optimizati
arXiv:2601.10015v2 Announce Type: replace Abstract: Personalized Federated Learning (PFL) excels at tailoring client-specific models, which is particularly critical for decentralized and heterogeneous
arXiv:2608.30450v1 Announce Type: new Abstract: Video virtual try-on aims to transfer a target garment onto a moving person across video frames. Current methods rely on human parsing masks or pose key
arXiv:2608.28982v1 Announce Type: new Abstract: Physics-integrated 3D Gaussian representations make it possible to simulate image-reconstructed assets directly as particles, but current Gaussia-MPM pi
arXiv:2608.29519v1 Announce Type: new Abstract: We introduce Function-Room Generation, a new indoor 3D scene generation setting that creates rooms supporting explicit functional goals rather than mere
arXiv:2608.29233v1 Announce Type: new Abstract: We present the winning solution to the ACM Multimedia 2026 Grand Challenge on Single-Image Guided Multi-Angle Image Synthesis. It ranks first among 293
Tool: GeoJSON Map Viewer I was helping Natalie gather some maps of local political boundaries (for the Granada Community Services District and the Midcoast Community Council and found a need to displa
arXiv:2502.00857v2 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly provide direct answers to user questions, raising concerns about reduced engagement in critical thinking a
I hadn’t realized it until now, but could Microduck actually be the biggest launch of a new consumer robot ever? 10,500 robots ordered and $4.54M in sales in just 4 days. It’s surprisingly hard to fin
I'm in San Francisco this week. So is the Deputy Prime Minister, but we’re here for very different reasons. He's meeting with Anthropic and OpenAI, working on Australia’s data centre pipeline. I'm her
arXiv:2608.29884v1 Announce Type: new Abstract: We show that sequence-level distillation from a capable long-context teacher model is a simple, annotation-free, and data-efficient strategy for improvi
In an interview in this article for The @guardian about AI deception, I explain why misaligned behaviors emerge from reinforcement learning, why they will continue to pose risks as models become more
arXiv:2608.29919v1 Announce Type: cross Abstract: The rapid proliferation of LLMs has further heightened the need to develop dependable AI-generated text detection, especially beyond English. Neverthe
arXiv:2608.29942v1 Announce Type: cross Abstract: The key limitation of current state-of-the-art influence-based guardrails is that they do not reliably distinguish a legitimate, user-authorized actio
Kaitchup just posted results of his benchmarks for Qwen3.8 27B for quants from different labs, Q4 to Q1, . All the details are hidden behind the paywall, but high level result is visible and looks lik
arXiv:2512.16391v2 Announce Type: replace-cross Abstract: Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG.
arXiv:2508.15757v2 Announce Type: replace Abstract: Configuration optimization remains a critical bottleneck in machine learning, requiring coordinated tuning across model architecture, training strat
arXiv:2505.16305v3 Announce Type: replace Abstract: While CANDECOMP/PARAFAC (CP) decomposition (CPD) is fundamental for tensor reconstruction, Bayesian CPD often scales poorly because variational upda
arXiv:2608.30682v1 Announce Type: cross Abstract: Learning materials properties from scarce labels and unlabeled crystals is a central challenge for data-driven materials discovery. We present SemiMat
arXiv:2608.30935v1 Announce Type: cross Abstract: Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodi
arXiv:2608.31102v1 Announce Type: cross Abstract: Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixtu
arXiv:2509.04183v3 Announce Type: replace-cross Abstract: The growing demand for scalable psychological counseling highlights the need for high-quality, privacy-compliant data, yet such data remains s
arXiv:2608.29304v1 Announce Type: new Abstract: Translating electroencephalography (EEG) into functional magnetic resonance imaging (fMRI) is important for medical neuroimaging, clinical brain-state m
MLCommons announced the release of MLPerf Storage v3.0 benchmark results, expanding the suite to cover the full spectrum of AI storage workloads, including an S3 object‑storage access layer in additio
arXiv:2608.28697v1 Announce Type: new Abstract: Additive manufacturing (AM) enables compact hydraulic components whose internal fluid channels can follow free-form 3D paths rather than conventionally
Hello! I've just uploaded a recent checkpoint of my model trained from scratch: https://huggingface.co/piotr-ai/polanka_3.7b_exp_wip_260901 It was pre-trained, mid-trained, and fine-tuned on a single