Knowledge catalogue
arXiv:2610.17665v2 Announce Type: new Abstract: Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipatin
arXiv:2610.14089v1 Announce Type: cross Abstract: Smart glasses are a promising platform for vision-language assistants, but private split inference remains expensive: protecting visual representation
arXiv:2610.19366v1 Announce Type: cross Abstract: Multimodal models and agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating informat
arXiv:2610.15417v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models activate only a few experts per token, but when their expert weights are offloaded to host memory, host-to-device (H2D)
arXiv:2610.19497v1 Announce Type: new Abstract: Data augmentation (DA) plays a vital role in improving model performance in low-resource or limited-supervision scenarios within Natural Language Proces
arXiv:2610.20456v1 Announce Type: new Abstract: The scaling relationship of compute and performance for language models (LMs) has been extensively studied; more recently, models are being designed to
arXiv:2610.17296v1 Announce Type: new Abstract: Emerging healthcare services, such as real-time diagnostics, remote health monitoring and computer-assisted surgery, require stringent Quality of Servic
arXiv:2610.16942v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are fast becoming a general interface to sound, yet how far their broad pretraining carries into specialized domai
arXiv:2610.20516v1 Announce Type: new Abstract: On-policy self-distillation provides dense supervision for reasoning models via a privileged self-teacher. However, this supervision reflects local toke
arXiv:2610.16927v1 Announce Type: new Abstract: Short-video search requires compact query rewriters that infer personalized intent from brief, ambiguous queries under strict latency constraints. The c
Small teams, short runway, and constant pressure to ship faster — it’s the reality we see every day among the founders we work with at Google for Startups. When you are building a company from the gro
arXiv:2610.16615v1 Announce Type: new Abstract: Visual token compression has emerged as a critical technique for reducing the inference cost of Vision-Language Models. Existing methods select tokens b
arXiv:2610.16102v1 Announce Type: cross Abstract: We argue that tacit knowing is better modelled as an operating regime of one memory substrate than as a kind of content. The substrate is VaCoAl, an a
arXiv:2610.16440v1 Announce Type: new Abstract: Medication recommendation requires jointly considering diagnoses, comorbidities, longitudinal patient history, and treatment interactions. Although rece
arXiv:2610.16322v1 Announce Type: new Abstract: Discovering behavioral patterns in open-ended games is challenging due to the lack of clear objectives or ground-truth annotations. In this work, we ext
arXiv:2610.16863v1 Announce Type: cross Abstract: Organizations pairing a human and a machine on a task decide, often by default, which executes each instance and what happens when both do. We account
arXiv:2610.18871v1 Announce Type: new Abstract: Sparse-to-dense motion completion recovers dense mesh motion from sparse vertex displacements. Residual priors trained on one geometry family frequently
arXiv:2610.14413v1 Announce Type: new Abstract: Computational coarse-graining aims to replace a sequence of updates with a cheaper module while preserving task performance. We present a continuation-r
arXiv:2610.14341v1 Announce Type: new Abstract: We present CoPlanVLM, which uses a Vision Language Model (VLM) to translate a single natural-language instruction and image into coordinated paths for a
arXiv:2610.16744v1 Announce Type: new Abstract: Video large language models (Video LLMs) encode each frame into hundreds of visual tokens, making video inference expensive. Existing methods reduce thi
arXiv:2610.18587v1 Announce Type: cross Abstract: Multimodal Emotion Recognition (MER) aims to understand human emotions by integrating information from multiple modalities such as speech and text. Ps
arXiv:2610.17684v1 Announce Type: new Abstract: High-fidelity surgical video generation is increasingly important for surgical education, simulation, and downstream AI training, as conventional simula
arXiv:2610.17671v1 Announce Type: cross Abstract: The design of ergonomic products and workspaces requires a deep understanding of human anatomy and posture. In particular, the head-neck-shoulder regi
arXiv:2610.18624v1 Announce Type: new Abstract: Pretraining generalist Earth observation foundation models requires data that combine several sensors, varied temporal sampling and, increasingly, text,
arXiv:2610.17009v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown strong potential for aligning generative models with human intent, but adapting RL to masked generative models (MG
arXiv:2610.14074v1 Announce Type: new Abstract: Large language models typically support different inference budgets through separate model sizes or fixed compute configurations. In multi-turn interact
arXiv:2610.14687v1 Announce Type: new Abstract: Many physical systems exhibit one-way coupling: exogenous fields such as medium density or obstacle geometry influence the dynamics without being affect
arXiv:2610.16066v1 Announce Type: new Abstract: Detailed video captioning has become an essential semantic interface for multi-modal understanding and generation. While existing methods mainly target
arXiv:2610.16980v1 Announce Type: cross Abstract: Artificial Intelligence (AI) models are increasingly developed, published and used across scientific fields. Researchers, students and industry profes
arXiv:2610.14654v1 Announce Type: new Abstract: Autoregressive video generators synthesize long videos through chunk-wise rollouts, yet they are typically trained to predict only the immediate future.
arXiv:2610.16349v1 Announce Type: cross Abstract: Which context tokens drive a language model's answer? Graph-based tools such as attention rollout and attention flow answer this from a single forward
arXiv:2610.15854v1 Announce Type: new Abstract: Grounded spatial reasoning about indoor scenes rests on a geometric reconstruction that the multimodal system does not itself produce. Feed-forward mult
arXiv:2610.16484v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models scale model capacity efficiently by activating only a small subset of experts for each input, while still requiring all
arXiv:2610.14944v1 Announce Type: new Abstract: Specifying segmentation targets with natural language provides flexible semantic conditioning for medical image segmentation. However, existing methods
There are more document parsing models than ever, and they’re getting harder to tell apart. That’s why we built OpenDocRouter. Every model we serve is benchmarked on ParseBench, with latency and cost
arXiv:2610.15570v1 Announce Type: cross Abstract: Settling one comparison between two truncation samplers has cost six thousand A100-hours, and nothing says in advance how far apart two samplers can b
arXiv:2610.15093v1 Announce Type: cross Abstract: AI coding agents operate in iterative loops: they modify code, run tools, inspect the results, and decide what to do next. We call the design of this
arXiv:2512.00724v3 Announce Type: replace Abstract: Reward models (RMs) are critical to reinforcement learning from human feedback (RLHF). However, policy models can exploit biases or spurious correla
arXiv:2610.18858v1 Announce Type: new Abstract: Multimodal large language models have advanced rapidly, but most remain optimized for single-image inputs. Multi-image reasoning is costly because each
arXiv:2610.15139v1 Announce Type: new Abstract: Linear-attention and state-space LLMs carry long context in a fixed-size recurrent state, and quantizing that state is the natural way to cut its cost d
arXiv:2610.17285v1 Announce Type: new Abstract: Modern neural-network training uses mixed recipes, assigning AdamW-like or sign-based updates to embedding and output layers and spectral updates to hid
I started Flama in 2018 to take a trained model to a production API with as little ceremony as possible. With 2.0 LLMs became first-class alongside classic models, and together with Miguel Durán-Olive
When we talk about agents, that doesn't necessarily mean we're talking about Python. In today's modern ecosystem, an agent might run as a high-concurrency Go microservice on Cloud Run, or live inside
i'm the maintainer of dodaios (formerly personal jarvis), an open-source ai agent app for the desktop. apache 2.0, runs on windows, macos and linux, no account and no cloud of ours between you and you
arXiv:2610.12496v1 Announce Type: cross Abstract: Sequence models with a fixed-size state avoid the quadratic cost of attention, but face a design choice. An input-dependent state transition gives con
arXiv:2610.13078v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires d
arXiv:2610.13144v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have emerged as a promising paradigm for enhancing complex reasoning through role specialization and collaboration,
arXiv:2610.12758v1 Announce Type: new Abstract: Language models have been adopted faster than evaluation practices that reliably assess their risks, and a growing share of use is affective rather than
arXiv:2610.06411v2 Announce Type: replace Abstract: Agentic systems increasingly coordinate molecular-design tools, but it is unclear which layer of the stack limits outcomes on real projects. We deve
arXiv:2610.13000v1 Announce Type: new Abstract: Language-model agents are used for specialized work such as financial research, healthcare and law. Such agents are often capable enough for a task but
arXiv:2610.13632v1 Announce Type: new Abstract: Large language model (LLM) agents are rapidly improving on long-horizon scientific and olympiad tasks. Recent systems have produced a Lean-formalized re
arXiv:2610.12957v1 Announce Type: cross Abstract: Embodied agents must translate multimodal observations and user requests into executable actions while adapting to product constraints, changing goals
arXiv:2502.01025v4 Announce Type: replace Abstract: Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is
arXiv:2512.02444v2 Announce Type: replace-cross Abstract: Joining heterogeneous tables requires different forms of correspondence, including exact agreement, syntactic transformation, semantic similar
arXiv:2610.13041v1 Announce Type: new Abstract: Recurrent-depth language models improve inference-time reasoning by repeatedly applying a shared network to refine internal representations, but the add
arXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still
arXiv:2610.13810v1 Announce Type: cross Abstract: Large language models (LLMs) are now a standard source of query expansion terms but they hallucinate. They inject non existent entities and off-topic
arXiv:2610.05031v2 Announce Type: replace Abstract: Large language models are increasingly used as integration layers above specialized tools, but a stronger component does not necessarily produce a s
Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's often the case that they can use their amortized cognitive su
arXiv:2610.11422v1 Announce Type: cross Abstract: Many dynamical systems generate influences whose consequences are not fully exhausted in the realized trajectory at the moment they arise. Such conseq