Knowledge catalogue
arXiv:2607.22483v1 Announce Type: new Abstract: The paper proposes a robot-agnostic compliant-control framework that extends the ROS control ecosystem with standardized joint and Cartesian command int
arXiv:2607.21995v1 Announce Type: cross Abstract: Rare-regime discovery in parameterized dynamical systems is an active-search problem: find one verified parameter at which a scientifically defined qu
I finished the speed leg of my spec-decode benchmarking for Qwen3.6-27B, main algorithms across quants. Overall: the heavier the quant, the more spec-decode buys you (10 of 10 speculative configs rank
arXiv:2607.22225v1 Announce Type: new Abstract: Safe autonomous navigation in shared environments requires the ability to anticipate and react to the latent behaviors of surrounding robots. In this pa
arXiv:2607.21866v1 Announce Type: new Abstract: Prior classical-ML learning-curve work fits power laws to tree, linear, and kernel models on tabular data, but at small scale: typically one curve, one
arXiv:2607.22530v1 Announce Type: new Abstract: Contact-rich robot manipulation requires physical interaction cues that are often invisible to cameras, making tactile sensing essential for robust cont
--> .abbel-fig { display: block; text-align: center; margin: 2.4em 0; line-height: 1.4; max-width: 100%; } .abbel-fig img { display: block; margin: 0.65em auto 0; height: auto; max-width: 100%; } /* I
I am seeing more and more videos as posts about how OpenAI is in complete financial ruin, Anthropic isn't much better. Their expenses go with the revenue they make etc etc. Meta made big investments i
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
If you run local agentic coding harnesses (Aider, Claude Code, etc.), prompt evaluation usually eats up most of your execution time. Every turn re-evaluates thousands of identical prefix tokens_system
I’ve spent the past month trying to find the point where an extremely small TTS model stops feeling like a size experiment and starts feeling genuinely useful. Today I’m releasing Inflect v2, with two
A little over a year ago I got frustrated trying to fine-tune SDXL on my RTX 3060. Every option either forced lower resolution, locked away important settings behind massive config files, or needed a
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
tests done power limiting the GPU on LACT - real power usage varies wildy at 20W it ranges from 25W to 56W same behavior happens on every setting prompt for the test runs: https://github.com/lukesdevl
arXiv:2607.20748v1 Announce Type: cross Abstract: Impact hammers, also known as rock-breakers, are essential machines in mining operations, where they perform secondary reduction. In underground minin
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:2607.21588v1 Announce Type: new Abstract: Learning effective robot manipulation policies requires diverse, high-quality demonstrations, yet existing data pipelines are often difficult to scale b
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:2607.20490v1 Announce Type: new Abstract: Edge Intelligence has emerged as a key paradigm for enabling real-time applications in smart cities by shifting computation from centralized cloud data
arXiv:2607.18020v2 Announce Type: replace Abstract: Physics-Informed Neural Networks (PINNs) solve PDEs by incorporating physical constraints into neural-network training, but large-scale problems are
If you want to get the most out of MTP. You have to run some tests / benchmarks to do so. Turning it on with defaults will get improvements, but for many models and card combinations, you are leaving
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:2508.11485v3 Announce Type: replace Abstract: Accurate and reliable navigation is crucial for autonomous unmanned ground vehicles (UGVs). However, current UGV datasets fall short in meeting the
arXiv:2607.20939v1 Announce Type: cross Abstract: Safe steerable catheter control is fundamentally a problem of interaction dynamics: the tip must follow a planned motion, remain compliant against mov
arXiv:2607.20723v1 Announce Type: cross Abstract: This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. L
arXiv:2607.20871v1 Announce Type: cross Abstract: Scaling semiconductor quantum dot arrays toward fault-tolerant quantum computing requires efficient tuneup of spin qubits, a process that depends on t
Model quantization has become essential for efficient large language model deployment, yet existing approaches involve clear trade-offs: methods such as GPTQ and AWQ achieve practical compression but
arXiv:2607.20806v1 Announce Type: new Abstract: Lightweight large language models (LLMs) are increasingly being deployed locally on personal computers and are expected to play a growing role in resour
arXiv:2607.20785v1 Announce Type: cross Abstract: Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficientl
arXiv:2607.20665v1 Announce Type: new Abstract: Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster res
arXiv:2607.20662v1 Announce Type: new Abstract: Laboratory automation accelerates discovery, yet its adoption is constrained by the high cost, proprietary design, and limited remote supervisability of
arXiv:2607.20652v1 Announce Type: cross Abstract: Language models are thought to exhibit the phenomenon of superposition, representing many more features than dimensions in their residual streams. Spa
I've been building a C99 inference engine from scratch (no Python, no BLAS, just gcc and make) that runs BitNet's ternary models on CPU. A few weeks ago I got obsessed with the matmul kernel - wrote a
arXiv:2607.20679v1 Announce Type: new Abstract: Estimating traversability in unstructured environments requires conditioning on robot embodiment, as the same terrain can be traversable for one platfor
arXiv:2607.20933v1 Announce Type: cross Abstract: Neural Source Code Summarisation (NSCS) aims to generate natural language summaries of source code to improve developers' and maintainers' understandi
arXiv:2602.20220v2 Announce Type: replace-cross Abstract: We investigate what specific design choices enable successful online reinforcement learning (RL) on physical robots. Across 100 real-world tra
arXiv:2607.19782v1 Announce Type: cross Abstract: Kernel methods are powerful tools in machine learning but commonly used full-Gram kernels face three key limitations: (1) quadratic scaling with train
arXiv:2607.19716v1 Announce Type: new Abstract: Pain is a complex and pervasive phenomenon affecting a large percentage of the population, and accurate assessment is essential for effective clinical m
arXiv:2607.19438v1 Announce Type: cross Abstract: Apple's M5 generation introduces a redesigned GPU architecture in which every core carries a dedicated Neural Accelerator: on-die matrix units exposed
arXiv:2607.19827v1 Announce Type: new Abstract: Ensuring safety in Physical AI systems operating in real-world environments is a critical challenge, particularly in hospital wards where vulnerable pat
TLDR: I (with the help of AI) re-implemented every Blackwell-only kernel (DeepGEMM, FlashInfer sparse-MLA, block-scaled FP8) in Triton, because they simply don't exist for sm89. The performance is 2-3
arXiv:2607.10170v2 Announce Type: replace Abstract: Communication graph rigidity is a fundamental requirement in many multi robot formation control approaches. However, ensuring and maintaining a rigi
In the past few months I’ve experimenting heavily and tortured my old 2016 Desktop PC to run the biggest Local LLM I can fit. I documented the whole process and research and I’ve published a repositor
arXiv:2607.16800v2 Announce Type: replace-cross Abstract: Variational Quantum Algorithms (VQAs) are a leading paradigm for near-term quantum computing, yet their training suffers from sensitivity to c
arXiv:2607.18135v1 Announce Type: cross Abstract: Learning-based approaches to locomotion have risen in popularity in recent years, showing the capability for complex legged locomotion and whole-body
arXiv:2607.19534v1 Announce Type: new Abstract: Haptic feedback provides an implicit channel for communicating safety intentions during human-robot shared control. Existing haptic guidance systems typ
arXiv:2607.19563v1 Announce Type: cross Abstract: Quantum error correction can be enhanced by post-selecting out runs that are likely to produce a logical failure, but the most accurate measures for t
arXiv:2607.19857v1 Announce Type: cross Abstract: Language-guided aerial perception aims to understand user-specified tiny targets in complex unmanned aerial vehicle (UAV) scenes. In real UAV deployme
arXiv:2607.19530v1 Announce Type: new Abstract: Many Blind and Low-Vision (BLV) people rely on guide dogs for moment-to-moment navigation, such as staying on path and avoiding obstacles and pedestrian
arXiv:2607.19901v1 Announce Type: new Abstract: Deep learning frameworks like nnU-Net achieve state-of-theart brain lesion segmentation performance but remain difficult to deploy in clinical research
arXiv:2607.19433v1 Announce Type: new Abstract: The transition from stateless generative models in artificial intelligence to stateful, autonomous agents represents an architectural evolution that, wh
arXiv:2607.19973v1 Announce Type: new Abstract: AI researchers describe state-of-the-art models as one thing repeated at scale: the Transformer, wired identically for text, pixels, or speech. Neurosci
arXiv:2607.20399v1 Announce Type: cross Abstract: Full-sized humanoid robot capabilities have grown exponentially in recent years, aiming towards general-purpose deployment in human environments. A po
arXiv:2607.18365v1 Announce Type: cross Abstract: Reinforcement learning (RL) for legged robots is advancing locomotion, demonstrating its ability to adapt to new and challenging terrain. Traditionall
TL;DR: Everyone says QLoRA past ~13B is dead on a 24GB card. I got the full 32B FLUX.2 dev transformer QLoRA-training resident on the GPU on a 7900 XTX under native ROCm on Windows (no ZLUDA, no CUDA
Scientists today face challenges of extraordinary scale and complexity. From shaping and simulating the intricate dynamics of fusion plasma, to exploring the vast search space of new materials, to mak
Paper:https://arxiv.org/abs/2607.19058 Code (GitHub):https://github.com/nuemaan/skewadam Hi everyone, I just published a preprint on a new optimizer designed to tackle the massive VRAM bottleneck in M
Hey everyone, I’m a Full-Stack Developer with 6+ years of experience. I’m relatively new to AI-assisted development workflows and want to build a production-ready, enterprise-level Next.js web applica
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 &
AlloyDB is a fully managed, PostgreSQL-compatible database service built for your most demanding enterprise workloads. It combines the best of open source PostgreSQL with Google’s advanced technology,