Knowledge catalogue
arXiv:2609.38384v1 Announce Type: new Abstract: Verified proof edits offer a natural source of supervision for improving language-model-generated Lean proofs. Yet verification establishes that an edit
arXiv:2609.40127v1 Announce Type: cross Abstract: Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keeping
arXiv:2609.39220v1 Announce Type: new Abstract: Process reward models (PRMs) have demonstrated notable effectiveness in test-time scaling and reinforcement learning by providing fine-grained signals f
arXiv:2609.38426v1 Announce Type: cross Abstract: We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models. LoopVL combines Module-Loop and Model-L
arXiv:2609.39628v1 Announce Type: new Abstract: This paper proposes MIND, a marginal-invariant neural dependency diffusion model for mixed-type tabular data. MIND does not directly learn the joint dis
arXiv:2609.39626v1 Announce Type: cross Abstract: Ensemble smoothers are the most successful and efficient techniques currently available for history matching. However, because these methods rely on G
pi-llama-skip-reasoning is an extension for the Pi.dev harness that forces a local llama.cpp model to stop reasoning and answer / act immediately. When you are deep into the ctx session and ask 27B a
arXiv:2609.38597v1 Announce Type: new Abstract: Unified Multimodal Models (UMMs) often rely on separate visual representations for understanding and generation, increasing visual context length and co
arXiv:2609.40287v1 Announce Type: new Abstract: Physics-constrained generative models aim to generate physical fields that match a target distribution and satisfy prescribed constraints. However, enfo
arXiv:2609.38974v1 Announce Type: new Abstract: Large language models are reshaping ecommerce from static recommenders into interactive shopping assistants, yet real-world shopping requires session-le
arXiv:2609.39518v1 Announce Type: new Abstract: Effective human-AI collaboration requires partners to establish references through interaction, which becomes fragile when descriptions are ambiguous, s
arXiv:2609.39149v1 Announce Type: new Abstract: Textual skills enable large language model (LLM) based agents to accumulate reusable procedural knowledge without updating model parameters. Yet existin
arXiv:2609.39045v1 Announce Type: new Abstract: Recent advances in large language models have made automatic game generation increasingly feasible, yet reliably improving generated games beyond a play
arXiv:2609.38832v1 Announce Type: new Abstract: Scaling attention parameters can improve language model quality, but retaining full token histories makes additional heads costly at long contexts. Furt
arXiv:2609.39109v1 Announce Type: cross Abstract: Parameter-efficient reinforcement learning aims to improve reasoning with a compact trainable interface to a pretrained model. We introduce the Thalam
arXiv:2609.38958v1 Announce Type: new Abstract: Large language models (LLMs) have been rapidly improving in long-context tasks, powered by Chain-of-Thought (CoT) reasoning. However, the internal mecha
arXiv:2609.39033v1 Announce Type: cross Abstract: CLIP is a powerful vision-language model, but it was not designed for fine-grained defect localization; CLIP-based anomaly detectors therefore adapt i
arXiv:2510.01581v2 Announce Type: replace-cross Abstract: Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in li
This is impressive! Face-to-face conversation is where AI interfaces are heading. @tavus gave me early access to Griffin, a video-to-video model that watches and listens as you talk. It can interrupt
arXiv:2511.17735v2 Announce Type: replace Abstract: Foundation models in several scientific domains, including visual domains, learn representations that capture complex semantics from their respectiv
vLLM's tensor parallel requires that several of the model architecture numbers be evenly divisible by the number of GPUs selected for tensor parallel. This usually means that you can only use a number
arXiv:2609.38802v1 Announce Type: cross Abstract: Uncontrolled repetition can prolong autoregressive generation in large language models (LLMs) and enable resource consumption attacks. Prior analyses
arXiv:2609.37025v1 Announce Type: new Abstract: As large language models (LLMs) advance, AI agents are increasingly deployed in open-world environments to tackle complex sequential tasks (e.g., docume
arXiv:2609.37236v1 Announce Type: new Abstract: An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested.
Building a local voice chat pipeline: Struggling with fast, natural PT-BR conversation models I'm currently trying to build a local AI voice chat system that can use tools via an LLM. I'm testing tw
arXiv:2609.38176v1 Announce Type: new Abstract: The dynamics of generative models exhibit two apparently distinct temporal windows: a speciation window, in which a sample commits to a semantic class,
arXiv:2609.35970v1 Announce Type: cross Abstract: Large language models are able to solve tasks whose answers depend on not only individual input tokens, but also on relations among them. How is such
arXiv:2609.36218v1 Announce Type: cross Abstract: Large language models are increasingly evaluated in specialized domains such as law, medicine, software engineering, and cybersecurity, yet film remai
arXiv:2609.35883v1 Announce Type: cross Abstract: Genome foundation models are growing into sparse mixture-of-experts (MoE) networks whose expert weights no longer fit on the machines that hold the se
arXiv:2609.36987v1 Announce Type: new Abstract: Graph databases are increasingly queried through natural language, yet every existing benchmark evaluates isolated single-turn queries rather than the m
arXiv:2512.20636v2 Announce Type: replace-cross Abstract: Many self-attention sublayers in large language models (LLMs) can be removed with little to no loss. We attribute this to the Attention Suppre
arXiv:2609.37852v1 Announce Type: new Abstract: Reliable FP8 attention remains a barrier to fully native 8-bit large language model training. We derive how forward-backward inconsistencies produce sta
arXiv:2609.37239v1 Announce Type: new Abstract: Many problems in sequential decision-making, such as imitation learning from observations, state-space compression, world-model learning, and sim-to-rea
Today, we’re expanding our ecosystem of managed remote MCP servers by introducing the Google Cloud CLI remote MCP server in preview. Powered by the popular gcloud and bq (BigQuery) command-line tools,
arXiv:2609.38152v1 Announce Type: new Abstract: We introduce FracGen, a fracture-aware video generation model that produces plausible, controllable fracture dynamics from a single image of an intact o
arXiv:2609.36161v1 Announce Type: cross Abstract: Can coding agents restore software that no longer runs while preserving its underlying methods, and reconstruct industrial software engines from open
arXiv:2609.38111v1 Announce Type: new Abstract: Vision-language models (VLMs) may accept false visual premises, answering questions about a target object's color, count, location, or state even when i
arXiv:2609.36892v1 Announce Type: new Abstract: As the capabilities of large language models (LLMs) continue to advance, increasing attention is turning to how to translate their abilities into useful
arXiv:2609.35800v1 Announce Type: cross Abstract: Low-bit key-value (KV) cache quantization saves storage but can sharply degrade vision-language model (VLM) accuracy. We introduce HeadGuard, a compos
arXiv:2609.35381v2 Announce Type: replace-cross Abstract: Many Model Context Protocol (MCP) servers wrap web APIs built for human developers, and their error messages tell the reader to run a command,
arXiv:2609.37574v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to enrich user queries in information retrieval (IR) so that a standard retriever such as BM25 can
arXiv:2609.36687v1 Announce Type: cross Abstract: Neural codecs encode continuous signals into compact sequences of discrete tokens, providing an interface for efficient transmission, storage, and tok
arXiv:2609.35833v1 Announce Type: new Abstract: Running a language model on edge hardware provides private and low-latency reasoning without a network connection, and yet the small models that fit on
arXiv:2609.37115v1 Announce Type: new Abstract: We revisit the role of appearance modeling in 3D Gaussian Splatting (3DGS) and show that limited expressiveness in view-dependent reflectance is a key d
arXiv:2609.34879v2 Announce Type: replace Abstract: Tool agents use large language models to act through external tools, yet successfully executed calls can still leave user requests unfulfilled. Tool
arXiv:2609.37011v1 Announce Type: cross Abstract: Federated learning enables multiple clients to collaboratively train models without sharing their private data. However, the lack of visibility into l
arXiv:2609.36086v1 Announce Type: cross Abstract: Language models are frequently employed to evaluate other language models. An LM evaluator scoring agentic behaviors across multiple criteria is valua
arXiv:2609.36521v2 Announce Type: new Abstract: Physical-field reconstruction and forecasting depend on both measurement density and spatial layout, yet evaluation under a single observation pattern d
I have a long list of my own domain specific eval questions that I run to validate which models I can rely on: coding, coding (numpy/pandas), data analytics decision making, local RAG, and voice assis
arXiv:2609.36322v1 Announce Type: cross Abstract: Chunked KV-cache compression reduces the memory and attention costs of long-context inference by compressing windows of consecutive tokens into fewer
arXiv:2609.38149v1 Announce Type: new Abstract: Transformer language models (LMs) are feed-forward: deep-layer representations are never fed back to shallower layers, and the only pathway for informat
I'm far from being an expert, but for me Qwen is not a Turbo Model so it cannot be as good as Krea 2 Turbo. Also their dataset seems to be not good, it's hard to make doodles, cartoon styles, and its
arXiv:2609.36121v1 Announce Type: cross Abstract: Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior. In this paper
arXiv:2609.36605v1 Announce Type: new Abstract: Understanding ongoing robot manipulation requires models to interpret visual observations in relation to interaction history and task progress. We intro
arXiv:2609.37583v1 Announce Type: new Abstract: Vision-language models can coordinate long-horizon robot manipulation, yet successful task reasoning still depends on whether local physical interaction
arXiv:2609.37283v1 Announce Type: new Abstract: Medical multimodal large language models (MLLMs) are increasingly expected not only to answer clinical questions, but also to localize the visual eviden
arXiv:2609.36890v1 Announce Type: new Abstract: In scientific machine learning, physical fields governed by partial differential equations exhibit low-rank structure and scale invariance. When solving
arXiv:2609.37055v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly operate in embodied and spatially grounded settings, where accurate understanding of depth, viewpoint, and th
arXiv:2603.15481v3 Announce Type: replace-cross Abstract: Data-free knowledge distillation enables model compression without original training data, critical for privacy-sensitive tabular domains. How
arXiv:2609.37169v1 Announce Type: cross Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since addi