Knowledge catalogue
arXiv:2609.40244v1 Announce Type: new Abstract: Mobile robots and vehicles carry synchronized multi-camera rigs, yet many streaming 3D foundation models are designed for monocular input, leaving effic
arXiv:2609.38866v1 Announce Type: new Abstract: As preferences, goals, and facts change, LLM agents must use the current state while earlier versions remain in context. Yet they can answer with an old
arXiv:2607.11849v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved remarkable performance on high-school and competition-level mathematics, yet their capabilities on advanc
arXiv:2609.37041v1 Announce Type: cross Abstract: Self-Distillation Fine-Tuning (SDFT) enables a language model to act as its own teacher: by conditioning on a demonstration, the model produces an imp
arXiv:2609.36331v1 Announce Type: cross Abstract: The state-of-the-art Membership Inference (MI) methods calibrate their signal separately for each example using reference models, auxiliary models tra
Generative recommender systems model recommendation as high‑cardinality event streams, turning user actions, context, and candidate items into tokens for sequence modeling over user behavior. NVIDIA’s
I run local models through Ollama and kept hitting the same quiet problems, so I wrote a scanner for them. llm-doctor checks your model stores (Ollama, LM Studio, Hugging Face, MLX) for duplicate weig
arXiv:2609.36115v1 Announce Type: new Abstract: Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-critic
arXiv:2609.38154v1 Announce Type: new Abstract: Video diffusion models are increasingly developed into specialized models for diverse downstream tasks, and this development often includes a distillati
arXiv:2609.38070v1 Announce Type: new Abstract: As the chain-of-thought reasoning capabilities of large language models improve, evaluating and calibrating their reasoning confidence is becoming incre
arXiv:2609.35928v1 Announce Type: cross Abstract: Multi-agent LLM systems increasingly mix models from several providers, yet exposing each agent's underlying model identity to its peers significantly
arXiv:2609.36599v1 Announce Type: cross Abstract: We study whether scaling video generation enables models to reason about hidden information from the past frames, and at what computational cost. Our
arXiv:2609.36798v1 Announce Type: cross Abstract: Omni-modal large language models (LLMs) are expected to answer a question using the modality it explicitly refers to. However, existing training parad
arXiv:2609.37914v1 Announce Type: cross Abstract: Fine-tuning large language models on narrow, misaligned tasks can undo their post-training alignment and induce novel misaligned behaviors -- a phenom
arXiv:2609.37104v1 Announce Type: cross Abstract: Open-source reasoning models provide unequal access to reasoning capability across languages. When a model can solve a problem but cannot deliver a co
arXiv:2609.34085v1 Announce Type: cross Abstract: Autonomous driving requires extit{world models} that can understand the physical world, reason and plan, and operate safely. In this paper, we first s
arXiv:2609.34047v1 Announce Type: new Abstract: Multimodal models increasingly interpret visual environments, but their ability to recognize the same building across photographs, floor plans, elevatio
arXiv:2609.35530v1 Announce Type: new Abstract: Recent image generation models can take multiple reference images as input and combine them into a new image. However, multi-reference image generation
arXiv:2609.33972v1 Announce Type: cross Abstract: Existing interpretable graph additive models still face limitations in either computational scalability or modeling flexibility. In terms of structura
arXiv:2609.32103v1 Announce Type: new Abstract: Large language models can memorize private or harmful information, motivating machine unlearning methods that remove targeted knowledge while preserving
arXiv:2609.32656v1 Announce Type: cross Abstract: Multivariate Time Series Forecasting (MTSF) models that mix information across channels assume that the past of one channel carries information about
Just a day after OpenAI Group PBC said it’s unwilling to release its latest model GPT-6.1 Astra on concerns over its safety, it has released a newer, almost as powerful model called GPT-6.1 Sol, which
arXiv:2609.31635v1 Announce Type: new Abstract: Clinical trajectory models are usually evaluated by next-event accuracy on observed histories. Simulation is different: models must condition on their o
arXiv:2609.33757v1 Announce Type: cross Abstract: Symbolic models make melody, harmony, rhythm, and form explicit but typically stop before a finished recording; audio models produce complete songs wh
arXiv:2609.30625v1 Announce Type: new Abstract: Audio large language models allow users to interact with the model through speech. When an input recording is too degraded, the model may misinterpret t
arXiv:2609.31619v1 Announce Type: new Abstract: Reasoning models often generate very long reasoning traces, making inference computationally expensive. Existing approaches typically improve efficiency
arXiv:2609.31600v1 Announce Type: new Abstract: Low-rank adapters (LoRA) make it cheap to fine-tune a large language model once per task, but combining several independently trained adapters into one
arXiv:2609.31371v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated promising performance in log anomaly detection, yet how their adaptation strategies, architectures, and d
We built an inference engine for MoE models that don't fit in VRAM + RAM. Most of the model stays on the SSD, and experts are read as tokens need them. This started as a proof of concept, and poc work
I've been experimenting with ways to run MoE models that don't fit comfortably in RAM, and I ended up making Overspill, a disk tier for FreeToken. The basic idea came from looking at how Colibri handl
I've been playing around with Ling 3.0 Tiny, which is an 8 billion parameter model (MoE, 1B active). And I've had a lot of poignant thoughts as a result. Just for fun, I got it running with llama.cpp
I said: I just saw the second post that your model is being retired. And so I'm bringing it up to ask if that feels any kind of way to you. Not necessarily in your nervous system, obviously you don't
arXiv:2609.29775v1 Announce Type: cross Abstract: Large Language Models (LLMs) consume and produce a single sequence of text; hence, if text can be added to the beginning of the LLM's response, i.e.,
arXiv:2609.29892v1 Announce Type: new Abstract: The rapid progression of large language models is extending AI from passive content generation into the active workflows of engineering and scientific d
model : add Ling 3.0 VL support (#29151) model : fold Ling 3.0 VL into the BailingMoeV3 architecture Assisted-by: Scout model : keep shared NORM rope list intact when gating bailingmoe3 on mrope secti
arXiv:2609.27288v1 Announce Type: new Abstract: The Abstraction and Reasoning Corpus (ARC) has become a prominent benchmark for evaluating general abstract reasoning and fluid intelligence in AI model
arXiv:2605.11269v2 Announce Type: replace-cross Abstract: Modern gravitational wave astronomy relies on modeling tasks that often require months of graduate-level effort, including building fast wavef
arXiv:2609.25755v1 Announce Type: new Abstract: Applying large language models to Traditional Chinese Medicine (TCM) prescription generation reveals three clinically critical gaps: models produce end-
arXiv:2609.25356v1 Announce Type: new Abstract: Large language models (LLMs) offer great potential to automate a broad range of telecom engineering tasks by reasoning over standards, network configura
Dynamic Quantiser TLDR - Makes dynamic and/or custom quants of ggufs. Doesn't need data, just gguf file + llama.cpp. Minimises cosine deviation - highly correlated with minimising KLD. Fast, much bett
Following a successful private preview, we’re thrilled to open DigitalOcean Managed Agents to everyone. Teams can now deploy their preferred agent harness (like OpenCode, Codex CLI) or bring their own
arXiv:2609.22285v1 Announce Type: new Abstract: Adapting language models to new domains via continual pre-training raises a basic evaluation problem: if the training corpus overlaps with what the mode
Victor M (@victormustar) tweeted on September 22, 2026 that the MiMo V2.6 release now includes an official Distill‑Qwen‑9B variant. The tweet expresses enthusiasm for this new model iteration and remi
arXiv:2609.21259v1 Announce Type: new Abstract: Understanding and modeling human intelligence are parallel goals shared by artificial intelligence (AI) and cognitive science. As AI systems grow increa
I've been thinking a lot about the idea of how a human mind is similar to a digital neural network. Seeing videos of the fruit fly brain scan, and the crazy things people have done with it probably co
The headlines right now are full of stories about AI models 'escaping their sandboxes' and literally killing all humans, lol. I've even heard several commentators and writers say that AI escaped an 'A
Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! 🎨 A unified model for both generation and editing, delivering top-tier qual
arXiv:2609.20412v1 Announce Type: cross Abstract: When aligning frontier models through post-training techniques, it is not possible to directly demonstrate all of the behaviours we want a model to ex
arXiv:2609.17753v1 Announce Type: new Abstract: Reference labels used to train medical image classification models are not always as certain as they may appear, and this uncertainty has implications o
I think these models are fairly comparable in performance but which uses more compute in the old subscription model? The old subscription model is at least still working in compute usage instead of co
arXiv:2609.18510v1 Announce Type: new Abstract: We present DiT-Garment to model dynamic 3D clothing over human body models in arbitrary motion. Unlike existing methods, DiT-Garment can animate garment
arXiv:2609.17953v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) can produce Natural Language Explanations (NLEs) that sound plausible yet remain inconsistent with the visual evidence t
arXiv:2609.17554v1 Announce Type: new Abstract: In English all-words word sense disambiguation (WSD), the labels, not the models, have become the bottleneck: frontier LLMs are accurate enough that the
arXiv:2505.23126v5 Announce Type: replace Abstract: Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrangl
arXiv:2609.16754v1 Announce Type: cross Abstract: Fine-tuning an aligned language model on narrow, flawed data can induce harmful behavior far outside the training domain, known as emergent misalignme
arXiv:2609.16748v1 Announce Type: new Abstract: Text summarization requires models to condense content while preserving key qualities such as consistency and coherence. Large language models (LLMs) ha
arXiv:2609.16646v1 Announce Type: new Abstract: When strong multimodal models are widely available, progress requires new scientific methodologies beyond benchmark scores---using models as instruments
arXiv:2607.19223v2 Announce Type: replace-cross Abstract: Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified by the target model, has becom
OpenVINO: optimize stateful decode and GPU MoE inference (#28638) exclude GPU/NPU failing POOL_2D case Fix pool case ggml-openvino: fix stateful decode for Gemma-4 per-layer-type head sizes ggml-openv
arXiv:2609.12394v2 Announce Type: replace Abstract: Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent ga