Knowledge catalogue
Fred Gao / Inside China: In a leaked four-hour investor talk, DeepSeek's Liang Wenfeng says the main US-China gap is compute access, Nvidia's CUDA moat is disintegrating, and more — In a rare four-hou
arXiv:2607.19355v1 Announce Type: new Abstract: LLMs are increasingly used with external knowledge sources like the internet. Do they weigh information appropriately -- updating more for reliable sour
arXiv:2607.20277v1 Announce Type: new Abstract: Machine learning models achieve high predictive accuracy in regression tasks, but their deployment in safety-critical and regulated domains requires int
arXiv:2607.17572v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences. Whil
arXiv:2607.19811v1 Announce Type: new Abstract: The Segment Anything Model 2 (SAM2) has advanced temporal promptable segmentation, yet its deployment remains hindered by heavy memory cross-attention o
arXiv:2607.20153v1 Announce Type: new Abstract: We study Gaussian averaging as a smooth surrogate for quantized neural models. Under bounded local oscillation, we derive a local dimension-dependent bo
arXiv:2607.19064v2 Announce Type: replace-cross Abstract: Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale
arXiv:2512.05462v2 Announce Type: replace-cross Abstract: Pharmaceutical drug discovery demands machine learning (ML) infrastructure that goes beyond general-purpose Machine Learning Operations (MLOps
arXiv:2607.19388v1 Announce Type: new Abstract: This work extends our one-dimensional single-sweep neural-operator studies to two dimensions. We consider one-group transport with isotropic scattering.
arXiv:2607.20372v1 Announce Type: new Abstract: Humans distill experience into reusable abstractions, e.g., strategies and cautionary reminders, and apply them to gradually solve problems more effecti
HPD-Parsing: Hierarchical Parallel Document Parsing We introduce HPD-Parsing, a lightweight (1B) and high-throughput document parsing model built on a Hierarchical Parallel Decoding paradigm. Unified
arXiv:2607.19624v1 Announce Type: new Abstract: The allocation of visual attention by pathologists during cancer diagnosis is a highly selective process that critically shapes the information extracte
arXiv:2607.20175v1 Announce Type: new Abstract: Frozen perception foundation models encode rich geometric, semantic, and dynamic knowledge. Yet narrow conditioning interfaces may attenuate task-releva
arXiv:2506.10386v2 Announce Type: replace Abstract: The burial state of anthropogenic objects on the seafloor provides insight into localized sedimentation dynamics and is also critical for assessing
arXiv:2607.18763v1 Announce Type: new Abstract: Magnetic resonance imaging comes in various modality contrasts that provide complementary anatomical and pathological information. Complete multimodal a
arXiv:2607.17612v2 Announce Type: replace Abstract: Continuous diffusion models have become the dominant paradigm for photo-realistic image Super-Resolution (SR), but they typically formulate reconstr
arXiv:2607.16195v2 Announce Type: replace Abstract: We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to reflect the compa
arXiv:2607.20142v1 Announce Type: new Abstract: We present a two-stage vision system that detects EEG cap electrodes in a live webcam stream and validates their anatomical placement in real time. A si
arXiv:2607.18540v1 Announce Type: new Abstract: Robotic perception pipelines increasingly rely on large vision backbones deployed on SWaP-constrained edge platforms, making post-training quantization
arXiv:2607.19678v1 Announce Type: cross Abstract: AI-generated answers in high-stakes domains are often fluent but difficult to verify, especially when they contain multi-step reasoning rather than a
arXiv:2607.19450v1 Announce Type: cross Abstract: Large-scale online reinforcement learning (RL) is the predominant means of eliciting advanced abilities including long-term reasoning and agentic tool
arXiv:2607.20033v1 Announce Type: new Abstract: The ability to acquire skills rapidly and effortlessly while retaining those already mastered is essential for robots. However, current methods still re
arXiv:2607.19877v1 Announce Type: new Abstract: Weakly supervised segmentation relies heavily on class activation maps (CAMs) to initially localize target regions. However, CAMs are often noisy and pr
arXiv:2607.19332v1 Announce Type: cross Abstract: Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching. Along the way, the underlying techniques ha
arXiv:2607.19701v1 Announce Type: new Abstract: VLMs are increasingly deployed in AD systems, creating an urgent need for rigorous safety evaluation under rare yet safety-critical scenarios. Among the
arXiv:2607.19146v1 Announce Type: cross Abstract: Cooperative perception enables autonomous vehicles (AVs) to improve situational awareness by aggregating detection outputs from multiple agents and se
arXiv:2510.16834v3 Announce Type: replace-cross Abstract: We present Schrodinger Bridge Mamba (SBM), a novel model for efficient speech enhancement by integrating the Schrodinger Bridge (SB) training
arXiv:2607.20368v1 Announce Type: new Abstract: Recent autoregressive video diffusion methods are increasingly built upon Self Forcing, where the student is trained on histories produced by its own ro
arXiv:2602.11072v2 Announce Type: replace Abstract: Simultaneous speech translation requires translating source speech into a target language in real-time while handling non-monotonic word dependencie
arXiv:2607.11557v2 Announce Type: replace Abstract: Knowledge distillation (KD) typically relies on the fixed perspective of a single teacher, limiting the diversity of supervisory signals. While mult
arXiv:2607.19357v1 Announce Type: new Abstract: Recent advances in recommender systems (RS) have shown substantial performance gains through generative modelling. In practice, recommendation often inv
arXiv:2603.18634v3 Announce Type: replace-cross Abstract: Rapid, large-scale 3D reconstruction from multi-date satellite imagery is vital for environmental monitoring, urban planning, and disaster res
arXiv:2607.18990v1 Announce Type: new Abstract: SWITi is a test-time method for reducing artifacts in tiled predictions, particularly for neural networks that learn posterior distributions from which
arXiv:2607.19524v1 Announce Type: cross Abstract: Federated learning (FL) offers a promising approach to privacy-preserving clinical risk prediction, but its deployment remains limited by restricted d
arXiv:2607.20003v1 Announce Type: cross Abstract: An increase in advanced Android malware requires the use of deep learning models, which can run on Android devices. But there is a trade-off between s
arXiv:2607.19390v1 Announce Type: new Abstract: A recent report finds that orthogonalizing the mLSTM memory matrix at read time (five Newton-Schulz iterations, trained through) substantially improves
arXiv:2511.12035v2 Announce Type: replace-cross Abstract: The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video g
Vultr has added support for the AMD Helios™ rackscale platform, which is driven by AMD Instinct™ MI455X GPUs. This allows the provider to offer high‑memory, GPU‑accelerated compute for enterprise work
arXiv:2607.14749v3 Announce Type: replace-cross Abstract: Music generation foundation models have recently attracted significant industry attention. However, achieving efficient generation and high-fi
arXiv:2607.19781v1 Announce Type: new Abstract: Autonomous driving requires understanding the road as a graph of drivable lanes and their connectivity, beyond the ego lane alone, to follow routes thro
arXiv:2607.18875v1 Announce Type: new Abstract: Millimeter-wave (mmWave) radar enables privacy-friendly human sensing, but its sparse point clouds are physical measurements of view-dependent electroma
arXiv:2512.02473v2 Announce Type: replace-cross Abstract: Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on p
Decoupling embedding from ingestion means whatever hardware is on hand can do the work. One script, runtime device check: MPS on Apple Silicon, CUDA on NVIDIA, CPU fallback otherwise. 10K-20K records
Lots interesting in this, but particularly: “Legitimate AI distillation used to create smaller, more efficient models plays a vital role in this open innovation ecosystem” Smol models getting govt sea
Disclosure: I work at NuMind, the team that trained NuExtract3. NuExtract3 is an Apache-2.0, open-weight 4B VLM based on Qwen3.5-4B. It is specialized for document understanding rather than general ch
The Claude Security plugin for Claude Code is now available in beta. Scan your changes for vulnerabilities before you commit, or run a full scan across your codebase, all from your terminal on the Cla
Elon’s original vision of an open, American AI was right. He could still flip Grok to open source which could be checkmate. Why? If you flip Grok open source, you necessarily move all margins out of t
I thought this was a very good post by @c_valenzuelab and really highlights how transformative video models already are for the businesses that are using them. I think video models are one of the most
lol so it’s possible that OpenAI’s guardrails prevented huggingface from being able to analyze the logs of attacks from… OpenAI’s model. so they had to switch to an open source Chinese model 😵💫 @Open
I've been building an AI that learns to play the classic Snake game through reinforcement learning. The goal is to reach high scores while keeping training time as low as possible. The current version
My 2hr workshop on Open vs Closed models, reward hacking, benchmaxxing & RL is out! 1. Closed vs open models 2. Throughput maxxing but accuracy minimizing 3. Benchmaxxing & cheating 4. Distillation &
Nice to see someone around here actually understand the technical details. (The vast majority of the attacks on me come from people who don’t.) And the probabilistic next-token critics were correct ab
Today we’re releasing Poolside Laguna S 2.1 It is a 118B-total, 8B-active open-weight model built for agentic coding and long-horizon work, with context up to 1M tokens https://poolside.ai/blog/introd
Hi everyone, We've open-sourced Tri-Net v2, the official implementation accompanying our recently published Scientific Reports (Nature Portfolio) paper: 'Tri-Net: Unified Deep Learning for Skin Lesion
Effective August 1st, 2026, we will be updating prices on select GPUs. This change reflects strong demand for advanced GPU capacity and helps us expand reliable access to high-performance compute for
Vibe coding isn't just for your PC anymore. Here's LLM Hub generating and previewing code entirely on an iPhone. Everything runs locally. Using the RunAnywhere SDK, Timmy Qian ported LLM Hub, an Andro
NVIDIA’s sixth‑generation NVLink is a purpose‑built scale‑up network that delivers up to 3.6 TB/s per GPU and 260 TB/s rack‑level bandwidth with 130 TFLOPS in‑network compute—outperforming off‑the‑she
arXiv:2607.14044v1 Announce Type: new Abstract: By 2030, 59 of every 100 workers will need reskilling or upskilling, yet the average time to close an enterprise skills gap grew from roughly 3 days in
arXiv:2607.13500v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have achieved strong performance in multimodal understanding, yet remain challenging to deploy on resource-constrained edg
arXiv:2607.13203v1 Announce Type: cross Abstract: False alarms remain a major barrier to deploying network intrusion detection systems (NIDS). In high-volume environments, even a sub-1% false positive