Search: “engineering”

arXiv:2610.19424v1 Announce Type: new Abstract: LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reason

£299.99 Lenovo IdeaCentre Mini (Snapdragon X1-26-100, 32GB, CPU only): - Qwen3.6 35B A3B coder: reads ~118 tok/s, writes 24.5, ~30 with MTP - Qwen3-Next 80B A3B: 17-18 tok/s writes with MTP How I got

arXiv:2610.17418v1 Announce Type: cross Abstract: Agentic workflows combine large language models with planning, memory, tools, execution environments, and iterative feedback. Their failures are diffi

arXiv:2610.16996v1 Announce Type: new Abstract: The penetration-resistant design of concrete structures requires the spatiotemporal evolution of the stress field within the target, whereas in design o

arXiv:2610.15308v1 Announce Type: new Abstract: Combining aerial robots with soft continuum manipulators promises safe, compliant interaction with the environment, but the coupled dynamics of a free-f

arXiv:2610.18523v1 Announce Type: new Abstract: Task planning for robots in off-site construction prefabrication is primarily manual, leading to planning inefficiencies and reluctance to adopt robotic

arXiv:2610.14021v1 Announce Type: new Abstract: Training multi-agent collaboration requires trajectories of checking, feedback, and repair, yet task-solving rollouts may end in immediate approval or r

arXiv:2610.14159v1 Announce Type: cross Abstract: Reward design remains a major bottleneck for reinforcement learning in robotic manipulation. Handcrafted dense rewards can compensate for the limited

arXiv:2610.14571v1 Announce Type: cross Abstract: Large Language Model (LLM) inference is driving a growing share of datacenter carbon emissions. Although carbon-aware scheduling can reduce these emis

arXiv:2610.15696v1 Announce Type: new Abstract: We present DRanker (Disney+ Ranker), a transformer-based multitask ranking model serving personalized recommendations on the Disney+ homepage. We descri

arXiv:2610.18018v1 Announce Type: new Abstract: Low-light image enhancement (LLIE) is an important image/video processing problem for reliable visual systems under poor illumination, yet it remains ch

arXiv:2610.18822v1 Announce Type: new Abstract: Egocentric human videos offer a scalable alternative to robot teleoperation for collecting dexterous manipulation data. However, two challenges limit th

arXiv:2610.17128v1 Announce Type: new Abstract: Egocentric video provides a continuous first-person record of everyday activities, making it a natural foundation for wearable AI assistants. Unlike off

arXiv:2610.18451v1 Announce Type: cross Abstract: Large-scale expert parallelism (EP) has become the standard deployment configuration for Mixture-of-Experts (MoE) models in production. Meanwhile, the

Reuters: Filing: OpenAI says a staffer who joined Apple sent 100+ files to a personal account and made a presentation about an unreleased product to Apple leadership — An OpenAI employee who left the

arXiv:2610.16569v1 Announce Type: cross Abstract: Relevance prediction between user queries and items is a fundamental component of e-commerce search systems. Traditionally, high-quality relevance lab

Every local setup I tried for Qwen-Image 2.1 meant a Python env, a node graph and an evening of picking quantization, offloading and resolution for my card. Kokon is a free, open-source desktop app th

Workplace artificial intelligence security startup Harmonic Security Inc. today announced it has raised 50 million in new funding to grow its platform for governing how employees use AI tools. The com

arXiv:2610.14123v1 Announce Type: cross Abstract: AI-assisted scientific discovery increasingly seeks to move beyond generating plausible ideas toward reproducible, constraint-aware workflows that can

arXiv:2603.21862v2 Announce Type: replace Abstract: Scaling laws govern macroscopic resource allocation for LLMs, yet precise architectural configurations for Mixture-of-Experts (MoE) models remain gu

arXiv:2606.19370v2 Announce Type: replace Abstract: Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data. It uses cheap, large-scale simulati

arXiv:2610.15639v1 Announce Type: new Abstract: Long-horizon robotic manipulation is inherently composed of semantically meaningful sub-tasks. While Movement Primitives (MPs) can model these component

arXiv:2610.16784v1 Announce Type: new Abstract: Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design

arXiv:2610.17804v1 Announce Type: cross Abstract: How can language models learn to optimize physical designs through experience? We introduce FracLearn, an experience-abstraction-generalization framew

arXiv:2606.12475v2 Announce Type: replace Abstract: Human-robot collaboration (HRC) combines the complementary strengths of humans and robots to improve task efficiency. However, many existing collabo

arXiv:2610.17099v1 Announce Type: cross Abstract: Local learning reduces cross-layer training dependencies, but an efficient accelerator must still retain operands, accumulate gradients, and select qu

New impressive work from Microsoft and collaborators. And it's one of my favorite recent topics: RL environments. They show that Qwen3.6-35B-A3B goes from 41.1 to 53.3 on Terminal-Bench 2.1 by trainin

Hello! We've been busy at Telperion with a lot of experimental research (more coming soon). Today, we're announcing the release of our latent attention variants of Qwen3.8-27B. Our latent attention va

arXiv:2610.18188v1 Announce Type: new Abstract: Learning robot policies from demonstrations is often limited by the cost of collecting diverse, high-quality expert data. While an appealing alternative

NVIDIA NeMo Gym is an open‑source evaluation environment that diagnoses failure modes and tracks error propagation across multistage chip‑design workflows. In Siemens’ Fuse EDA case, the Gym was used

arXiv:2610.16592v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) is commonly used to enhance the capabilities of large language models (LLMs) in solving complex multi-turn tasks.

arXiv:2512.03923v3 Announce Type: replace Abstract: Solving reservoir seepage partial differential equations (PDEs) is critical for hydrocarbon development optimization and production forecasting. Con

arXiv:2604.07379v2 Announce Type: replace-cross Abstract: From butterfly wings to remnants of nuclear detonation, aperiodic order repeatedly emerges in nature, often exhibiting reduced sensitivity to

arXiv:2610.14519v1 Announce Type: new Abstract: Effectively eliciting the capabilities of large language models (LLMs) at inference time remains an important challenge. Existing studies address this c

Sampling: temp 1.0, top_p 0.95, top_k 20 for both. Run with evalscope over the OpenAI-compatible API: Qwen3.8-Next on Strata (MI50 32GB), Qwen3.8-27B on llama.cpp (RX 7900 XTX 24GB). Caveat: These are

arXiv:2605.06046v2 Announce Type: replace Abstract: Auto-regressive token generation in large language models is memory-bound because it requires 'attending to' key and value tensors (KV cache) of all

Scaling code generation without scaling review risks turning coding gains into a larger “review” backlog (whether during PR review or later, when dealing with technical debt, incidents, or bugs). The

arXiv:2610.16297v1 Announce Type: new Abstract: Scaling laws predict large-model performance from small experiments, but finding a reliable law itself requires costly experiments. SLDBench tests wheth

As strata is somewhat new, I assume that some people din't yet learn how to finetune it for best performance on their machine. I find documentation a bit hard to navigate (use your agents for this!),

arXiv:2610.14105v1 Announce Type: cross Abstract: Accurate artery extraction from X-ray coronary angiography (XCA) is essential for coronary artery disease diagnosis and intervention. However, low ves

arXiv:2610.16977v1 Announce Type: new Abstract: Visual in-context learning (ICL) enables vision-language models (VLMs) to adapt at test time via demonstration examples, but its effectiveness depends c

Today I'm excited to share that New Material is joining @MistralAI to design sovereign frontier AI. We're establishing a new team, 'Solutions Design' within Mistral: working across product, engineerin

You can't solve real-world physical tasks through autoregressive sampling alone. The physical world is entirely unforgiving to hallucination or approximate pattern matching. If we want actual autonomo

Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes and results, those logs can become training data for the mode

David Silver is one of the all-time greats. He was the creator of AlphaGo, which changed the course of history by showing that neural nets could achieve superhuman performance for the first time. He a

A coding agent finishes a change and wants to open a GitHub issue with a link to its results. The agent can describe the issue, but creating it belongs to a different system. It needs a tool that can