Knowledge catalogue
DISCLAIMER: the prefill rate on the dashboard in the video counts cached prompt tokens as if they were read again, so it reads high. The captions show the server’s real end-to-end numbers, and so does
And now let’s get it started! 💃 https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017 🔓 Open-source release Get DeepSeek-V4.1-Flash-1017: 🤗 Hugging Face: https://huggingface.co/deepseek-ai/DeepS
I have never used any Anthropic models, so if anyone has used both, please tell me which one is better at coding. Please don’t include benchmark comparisons. I don’t trust them. Thankyou submitted by
I use Pi/OpenCode for coding tasks which still seems to be the most popular, but I'm wondering what you guys use for normal chat interface. It's been a few months since I've seen discussions about har
Working on getting our US hosts up and running. Very soon! 🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a P
model: add Beam (Reflection) (#30670) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/56841237 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (a
arXiv:2610.22256v1 Announce Type: new Abstract: Reducing memory use in large language model (LLM) training is an ongoing challenge. Activation checkpointing saves memory by recomputation, while lossy
arXiv:2610.21294v1 Announce Type: new Abstract: Transformer-based language models have shown strong capabilities across many tasks and domains. However, prior work shows that, for a given task, not al
arXiv:2610.22187v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in computational social science to assign scalar scores to social and psychological constructs. How
arXiv:2610.22167v1 Announce Type: new Abstract: Understanding a conversation requires connecting what is said to the speakers' relationships, expectations, and earlier exchanges. Prior work shows that
arXiv:2602.05708v2 Announce Type: replace-cross Abstract: Large language models (LLMs) offer a compelling approach to entity matching (EM) in label-scarce settings, yet their matching quality is sensi
arXiv:2610.21597v1 Announce Type: cross Abstract: Reverse engineering the data formats used by mobile software is skilled and slow, and using AI to assist with it is attractive. We evaluate this for t
arXiv:2610.22340v1 Announce Type: cross Abstract: How can robots autonomously collect the contact-rich experience needed to learn dexterous manipulation? We present DSP: Dexterity from supervised play
arXiv:2610.21654v1 Announce Type: new Abstract: This paper presents the Digital Typhoon Dataset V3, a new version of the longest typhoon satellite image dataset spanning nearly 50 years, designed to b
arXiv:2610.21327v1 Announce Type: new Abstract: Multimodal long-document question answering requires models to seek sparse evidence across pages and modalities, understand heterogeneous document conte
arXiv:2610.21368v1 Announce Type: cross Abstract: With the expansion of pre-trained language model usage in recent years, the importance of datasets for performing tasks in specialized domains has sig
arXiv:2504.00070v2 Announce Type: replace Abstract: This paper introduces Fuzzy Attention Network-Based Transformer (FANTF), an approach for time series forecasting, classification, and anomaly detect
arXiv:2610.21246v1 Announce Type: new Abstract: Large language model (LLM)-guided Bayesian optimization (BO) uses past observations to guide search, but proposed directions and their revision can rema
arXiv:2610.21720v1 Announce Type: cross Abstract: Federated LLM unlearning addresses targeted knowledge removal when forget and retain data remain distributed across private clients and are inaccessib
arXiv:2610.20814v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards often trains language models on responses generated by a different, possibly stale behavior policy. Cor
arXiv:2610.20776v1 Announce Type: cross Abstract: LLM-based agents increasingly execute long-horizon, end-to-end workflows involving shell commands, code modification, dependency installation, and int
arXiv:2610.22273v1 Announce Type: cross Abstract: Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottle
In October 2026 Georgi Gerganov posted that he ran **llama.cpp v0.7.0 on a 128‑GB‑RAM Mac (Spark)**, serving the Qwen3.8‑Flash‑Next GGUF model in IQ4_NL precision. The command used was `llama serve -h
arXiv:2610.22320v1 Announce Type: new Abstract: Recent advancements in diffusion models have significantly improved text-to-image generation, enabling their application to visual storytelling, where c
arXiv:2602.18891v2 Announce Type: replace-cross Abstract: Advances in large language models (LLMs) are rapidly transforming scientific work, yet empirical evidence on how these systems reshape researc
arXiv:2610.21134v1 Announce Type: new Abstract: Predicting live birth before fresh embryo transfer could support shared decision-making in IVF/ICSI, but routine clinical data are small, heterogeneous,
arXiv:2610.21333v1 Announce Type: new Abstract: Natural language messages often contain quasi-identifiers that are weak in isolation but can jointly reveal an individual's private attributes. We call
Startup Reflection AI Inc. today made the weights of Beam, its first large language model, available on Hugging Face. The company also released technical resources that will enable developers to custo
arXiv:2610.21739v1 Announce Type: cross Abstract: As agents powered by foundation models move into open-ended environments, continual learning from experience becomes essential. For agents built on mo
arXiv:2610.22264v1 Announce Type: new Abstract: Reinforcement learning (RL) enables language models to improve text-to-image (T2I) generation by rewriting prompts for a frozen image generator. Existin
arXiv:2610.21896v1 Announce Type: new Abstract: Hyperspectral images (HSIs) are often corrupted by Gaussian noise, impulses and stripes whose intensities vary across bands. The representative coeffici
arXiv:2610.20866v1 Announce Type: cross Abstract: Realistic traffic simulation and autonomous planning both depend on modeling interactions among heterogeneous road users whose dynamics, constraints,
arXiv:2610.20926v1 Announce Type: new Abstract: Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience. Building on t
arXiv:2610.20826v1 Announce Type: new Abstract: We investigate whether per-layer, per-task-phase (prompt/reasoning/response) expert-routing statistics in a Mixture-of-Experts (MoE) language model can
arXiv:2610.21746v1 Announce Type: cross Abstract: Many collective-action systems are neither fully decentralized nor fully centralized: agents voluntarily organize into institutions that share organiz
Hi! I sometimes train models and one thing always seemed very suboptimal for me. This is VAE latent files that take much more space than original data, while VAE should compress data, not making it mo
arXiv:2610.20778v1 Announce Type: cross Abstract: Automating organizational work means answering many small typed questions about one piece of state (does this email need a reply, how urgent is it, wh
arXiv:2610.21330v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for election information, yet little is known about how external web content shapes the political i
arXiv:2610.20898v1 Announce Type: cross Abstract: Reinforcement learning with self-generated labels, such as majority vote over a model's own samples, often recovers most of the gain of training with
arXiv:2505.12242v4 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) often exceeds GPU memory limits, prompting systems to offload model states to CPU memory. However, ex
arXiv:2610.21320v1 Announce Type: cross Abstract: Detailed captions transfer visual information into vision-language model supervision, but quality is easily conflated with length: long single-pass ou
arXiv:2610.19183v1 Announce Type: new Abstract: Existing biomimetic lower-limb prosthesis controllers are commonly designed for discrete locomotion modes, requiring separate parameterizations for leve
arXiv:2610.20474v1 Announce Type: new Abstract: Pretrained vision-language-action models (VLAs) often fail midway through unseen long-horizon tasks. Recursive self-improvement (RSI) offers a remedy, b
arXiv:2610.14697v1 Announce Type: cross Abstract: Speech-conditioned generation maps speech signals to target audio outputs. Prior end-to-end speech-conditioned generative models achieve high fidelity
arXiv:2610.19613v1 Announce Type: new Abstract: As machine unlearning for multimodal large language models (MLLMs) rapidly advances, rigorous evaluation of its effectiveness becomes increasingly impor
arXiv:2610.15855v1 Announce Type: new Abstract: We study how to detect and mitigate visual attention sinks in vision-language models (VLMs). Visual attention sinks are image tokens that absorb a large
arXiv:2610.19560v1 Announce Type: cross Abstract: In long-horizon tool-calling tasks, LLM agents can fail not only because of tool-use errors, but also because of ineffective interaction with users. Y
vulkan : fix concurrent first device init (#29766) vulkan : fix concurrent first device init tests : load models in parallel in test-thread-safety Loading them serially never exercised concurrent firs
arXiv:2610.19097v1 Announce Type: new Abstract: As the Arctic transitions toward a seasonally ice-free state, capturing the complex morphology of submerged sea ice is crucial for advancing models of o
arXiv:2610.19084v1 Announce Type: cross Abstract: Automatic prompt optimization (APO) uses feedback from model responses to improve prompts automatically. However, its effectiveness is usually measure
arXiv:2610.18240v1 Announce Type: new Abstract: Multi-agent debate (MAD) aims to improve large language model reasoning by exposing agents to alternative solutions and enabling iterative revision. How
arXiv:2610.14877v1 Announce Type: new Abstract: Experience-based learning enables large language model (LLM) agents to improve over time by reusing knowledge from past executions. However, existing me
arXiv:2610.16117v2 Announce Type: new Abstract: LLM-based multi-agent collaboration is increasingly used to solve complex tasks by dividing work among specialized agents and integrating complementary
arXiv:2610.19882v1 Announce Type: new Abstract: Instruction-driven image editing has reached native 4K, yet how such editors are trained remains undisclosed, and pretraining one from scratch is beyond
arXiv:2610.19578v1 Announce Type: cross Abstract: Graph Collaborative Filtering models have achieved remarkable success in recommendation systems. However, they inherently suffer from a catastrophic r
arXiv:2610.18052v1 Announce Type: new Abstract: Long-term memory has become a core component of large language model (LLM) agents. As agents accumulate personal information over long-term use, users i
arXiv:2609.35089v2 Announce Type: replace Abstract: Meta-analysis is the synthesis of information from multiple sources to arrive at an overarching conclusion. There is a large need for meta-analysis
arXiv:2610.20012v1 Announce Type: new Abstract: Chemistry evaluation has moved past multiple-choice probes toward open-ended expert problems, yet the benchmarks that define the current frontier still
arXiv:2610.17358v1 Announce Type: cross Abstract: Formal verification proves that a program satisfies its specification, but says nothing about whether the specification captures what the author meant
arXiv:2603.26030v2 Announce Type: replace Abstract: In practical structural design and solid mechanics simulations, material properties inherently exhibit random variations within bounded intervals. H