Knowledge catalogue
arXiv:2608.14913v1 Announce Type: cross Abstract: We introduce the Open-Strategy Dictator Game (OSDG), a variant of the classic dictator game in which each player's strategy is a natural-language docu
arXiv:2608.14838v1 Announce Type: cross Abstract: Retrieval components for code assistants are tuned against retrieval metrics: a configuration that raises recall@k is adopted, and downstream task suc
arXiv:2608.16391v1 Announce Type: cross Abstract: As large language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the eco
We just released TensorRT Model Connect in Public Preview. You can take a supported @huggingface model to end-to-end TensorRT inference in just two commands. No intermediate ONNX export, and the resul
arXiv:2608.14329v1 Announce Type: cross Abstract: Principle-based regulation, with evaluative standards such as 'fair, clear, and not misleading' or 'deliver good outcomes', cannot be reduced to binar
arXiv:2604.01413v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG)
arXiv:2608.14016v1 Announce Type: cross Abstract: Live game commentary is scarce: it exists for professional esports broadcasts and almost nowhere else. We present a content-based video narration syst
arXiv:2608.13566v1 Announce Type: cross Abstract: Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.g., SWE-bench and LiveCodeBench) as eviden
arXiv:2608.13799v1 Announce Type: new Abstract: This paper presents an event-driven learning and benchmarking framework for the Dynamic Multi-Depot Vehicle Routing Problem with progressively revealed
arXiv:2608.14481v1 Announce Type: cross Abstract: As heterogeneous robotic systems deploy across diverse urban zones, maintaining safety amid complex human-robot interactions remains a critical challe
I created 3 SVG prompts, each one rather hard. Perspective: A animated drone view perspective on a park. Beauty: A beach scene with an evil cat Composition: An AGI breaking out of a virtual sandbox pr
arXiv:2608.13958v1 Announce Type: new Abstract: How do we govern AI systems whose reasoning we cannot fully inspect? Governance does not require understanding a system's reasoning. It requires stating
Its interesting to see the experiments on how to give AI a computer: Codex & Claude Code use your local machine, ChatGPT Work on the web (as well as Claude and ChatGPT) give the AI a one-time machine
arXiv:2608.13807v1 Announce Type: cross Abstract: Peripheral nerves buried beneath intact tissue are difficult to visualize during surgery and remain inaccessible to white light wide-field imaging and
arXiv:2608.14114v1 Announce Type: new Abstract: As the integration of volatile renewable energy sources increases the strain on modern power grids, the use of Reinforcement Learning (RL) for autonomou
arXiv:2608.13567v1 Announce Type: new Abstract: The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about o
Ollama has the best performance for deepseek v4 flash on average. For local only, you can try qwen3.8 that is optimized: Apple Silicon: ollama run qwen3.8:27b-mlx NVIDIA: ollama run qwen3.8:27b Benchm
arXiv:2608.14094v1 Announce Type: cross Abstract: Cloud-local LLM inference systems have the potential to use the reasoning capability of large cloud models while protecting sensitive user data on per
arXiv:2608.14284v1 Announce Type: cross Abstract: Fine-grained robotic evaluation matters for understanding embodied models, going beyond binary success rates and rule-based process scores. We present
arXiv:2608.13563v1 Announce Type: cross Abstract: Early-stage teams often lack users, time, and budget to run repeated UX studies, yet still need decision-oriented signals to iterate safely. We study
Thought i would just add my own flags here for llama.cpp (literally pulled and rebuilt latest today). Running on a 4090 FE and 48gb of DDR4 ram on WSL2. Basically you have 3 knobs you can tune for max
Yes, it sucks to waste time waiting on 16K+ reasoning tokens alone. But here's the thing, this is only a 27B model trying to perform on par with 1T+ parameter models. Something has to be sacrificed, a
arXiv:2510.05740v2 Announce Type: replace-cross Abstract: The rapid development of generative models has made it increasingly crucial to develop detectors that can reliably detect synthetic images. Al
arXiv:2608.14122v1 Announce Type: new Abstract: Production scheduling in complex manufacturing environments is challenging when sequence-dependent setup times, stochastic disturbances, and due-date co
arXiv:2608.14157v1 Announce Type: new Abstract: Mechanical ventilation is a critical life-support intervention, requiring dynamic adjustments to ventilator settings as a patient's condition evolves. W
arXiv:2608.14021v1 Announce Type: new Abstract: Transformer-based sequential recommenders with causal self-attention often rely heavily on the most recent interaction at inference time, but how this b
arXiv:2608.14426v1 Announce Type: new Abstract: AI is increasingly being used to help with AI R&D. Under certain conditions this feedback loop might be able to produce an intelligence explosion, with
DeepSeek V4 Pro (Aug 2026) has been released on the Together AI platform. The model employs a 1.6‑terabyte Mixture‑of‑Experts architecture with a 1‑million‑token context window and supports three dist
Hugging Face: Hugging Face says developers made 151K+ derivatives based on Qwen models, topping others, making Qwen one of the largest foundations in the open model ecosystem — In the AI world, time f
Single prompt 'make me a 3d scene of an anime girl' (stolen from someone on discord, I like it a lot since it seems like every model struggles a lot with it) Everything is one shot. No vision, no iter
Honestly I am surprised at the speed and performance I am getting from the model, it does not allow for complete hands off like Claude 5.0 but that is not what I want, i want to be able to iterate and
Bloomberg reports Stripe agreed to buy model router OpenRouter for over $7B; Stripe has not confirmed the deal.
https://github.com/alekk89/llama-cpp-windows-manager It has been three months since I first shared my personal solution for running llama.cpp on Windows, and the project has evolved considerably since
arXiv:2608.13329v1 Announce Type: new Abstract: A model that behaves differently when it senses it is being tested would undermine the evaluations we rely on, so recent work has sought to read that se
arXiv:2608.12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs). Yet agreement in final labels does not sh
Anthropic PBC today revealed that it has developed an artificial intelligence model more capable than Claude Mythos 5. The company detailed the algorithm in the latest edition of its AI alignment repo
I'm currently building a very budget-oriented AI / homelab PC using used parts. I've been saving up (I'm a student), and I'm working on a setup costing around 330€ total. The specs are: Xeon E-2124: N
arXiv:2606.21202v2 Announce Type: replace-cross Abstract: Reaching global agreement from purely local interactions is a defining problem of collective intelligence, and most models of it assume that a
arXiv:2608.13387v1 Announce Type: new Abstract: On-policy distillation (OPD) supervises a student language model on trajectories sampled from its current policy, but assigns equal credit to response t
damn deepseek moves fast on roon tweets the major ai companies should commit to a real time priced API product. ai demand varies wildly over a day/night curve and the industry is broadly extremely cap
arXiv:2608.13415v1 Announce Type: cross Abstract: We consider the problem of autonomously learning robot skills under a limited practice budget for sequential tasks. We propose an active skill learnin
arXiv:2608.12345v1 Announce Type: new Abstract: Language models are increasingly deployed as co-scientists, yet their ability to uphold research integrity under institutional pressure remains unmeasur
arXiv:2608.13489v1 Announce Type: new Abstract: We present extbf{DreamX-Phi 1.0}, an action-conditioned video world model for robotic manipulation that, given an observed frame, a language instruction
arXiv:2608.12746v1 Announce Type: cross Abstract: Object hallucination in multimodal large language models arises when language priors and corpus co-occurrence bias outweigh the visual evidence, with
arXiv:2608.12363v1 Announce Type: cross Abstract: European countries are debating policies to mitigate the increased energy costs caused by renewed geopolitical tensions, while pursuing decarbonizatio
arXiv:2608.12831v1 Announce Type: cross Abstract: Online platforms increasingly compare many adaptive decision policies---ranking systems, recommendation algorithms, pricing rules, and language-model
arXiv:2602.17045v2 Announce Type: replace Abstract: A growing body of work attempts to evaluate the theory of mind (ToM) abilities of humans and large language models (LLMs) using static, non-interact
arXiv:2608.13344v1 Announce Type: new Abstract: Long-horizon Earth observation reasoning requires models to organize multi-stage geographic evolution, localize spatial changes, detect temporal anomali
arXiv:2608.12339v1 Announce Type: cross Abstract: Large Language models (LLMs) were found to be susceptible to a host of social, affective, and cognitive biases. We examined two mechanisms through whi
arXiv:2608.13210v1 Announce Type: cross Abstract: Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting s
neurosymbolic world models – *exactly* what I argued for in 2020 in the Next Decade in AI – for the win. Jeremy's excellent work here is a great illustration of a very powerful type of approach: LLM-g
Open models are improving at an unprecedented rate. Congrats to the whole @Zai_org team. Ollama will support GLM-5.3 upon the open release! ❤️ Get ready to code. Introducing GLM-5.3: Built to Code. Re
mlx-dspark is an MLX port of DeepSeek's DSpark speculative-decoding drafters (the DeepSpec release), plus z-lab's DFlash, with one lossless verify loop. v0.10.0 adds Qwen3.8-27B via RadixArk's drafter
arXiv:2608.13103v1 Announce Type: new Abstract: Long-horizon surgical robot manipulation is challenging because task rewards are sparse, while meaningful interaction changes occur at irregular interva
arXiv:2608.13341v1 Announce Type: cross Abstract: Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Convent
Something has happened with post-training as shown by DeepSeek flash & GLM-5.3 updates. Same base, big improvement in perf to frontier levels. Can't explain this by even logit distillation etc These a
arXiv:2608.13297v1 Announce Type: new Abstract: In evolutionary search, a weak child can be a valuable ancestor that makes high-fitness regions reachable. Immediate-return control is blind to this del
arXiv:2608.13453v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as generalist robotic policies capable of following diverse language instructions and performing a wi
We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world
arXiv:2608.12322v1 Announce Type: cross Abstract: Self-reflection is widely assumed to improve LLM reasoning, yet which component drives the gain remains poorly understood. We present a controlled six