Atomizer-IO: Beyond Pixels, Patches and Grids
arXiv:2609.40320v1 Announce Type: new Abstract: Most vision architectures assume that observations lie on a regular grid, an effective abstraction for natural images but a restrictive one for sensing
Knowledge catalogue
arXiv:2609.40320v1 Announce Type: new Abstract: Most vision architectures assume that observations lie on a regular grid, an effective abstraction for natural images but a restrictive one for sensing
arXiv:2609.40097v1 Announce Type: new Abstract: Existing auto-research benchmarks often entangle multiple sources of improvement, including training frameworks, hyperparameters, compute budgets, and d
arXiv:2609.39166v1 Announce Type: new Abstract: Persistent spatial memory enables embodied agents to navigate familiar environments across repeated visits. However, targets may move while unobserved,
arXiv:2609.38660v1 Announce Type: cross Abstract: Long-form subtitle translation requires reasoning over discourse and cultural context spanning episodes or entire series, while maintaining consistent
arXiv:2609.38908v1 Announce Type: cross Abstract: Single-cell transcriptomics enables profiling of cellular states at unprecedented resolution, but its high dimensionality, sparsity, and technical bat
arXiv:2609.40048v1 Announce Type: new Abstract: Ultra-long video temporal grounding requires balancing long-range evidence search with fine-grained event understanding under a limited visual budget, y
arXiv:2609.40067v1 Announce Type: cross Abstract: Community Notes is a crowd-sourced approach for adding context to posts on X. Contributors propose and rate notes, forming the inputs to an open-sourc
arXiv:2609.39263v1 Announce Type: new Abstract: A concept subspace's effect on model behavior does not establish how it relates to the output readout. We introduce a two-sided geometric diagnostic tha
arXiv:2609.39096v1 Announce Type: new Abstract: Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows with the generated history. Existing compre
arXiv:2609.39148v1 Announce Type: new Abstract: AI agents can externalize what they learn from past tasks into reusable skills, such as procedures, checklists, code, or other executable artifacts, tha
arXiv:2609.39371v1 Announce Type: new Abstract: In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements refer
arXiv:2609.38758v1 Announce Type: new Abstract: Referring Video Object Segmentation (RVOS) aims to produce a pixel-accurate mask sequence for an object specified by natural language. Sa2VA combines a
arXiv:2609.40230v1 Announce Type: cross Abstract: Visual perception is conventionally formulated as a one-shot prediction from a single glance at the image, under the assumption that the image content
arXiv:2609.39128v1 Announce Type: new Abstract: Global video geo-localization aims to infer the geographic location of a video worldwide, evaluating performance across four geographic hierarchies: cit
arXiv:2609.40303v1 Announce Type: new Abstract: Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnatio
arXiv:2512.19735v4 Announce Type: replace Abstract: Accurately predicting mortality risk in intensive care unit (ICU) patients is critical for clinical decision-making. Large language models (LLMs) ar
arXiv:2609.39380v1 Announce Type: new Abstract: Reliable infographic generation requires facts, symbols, and visual relations to remain consistent through rendering and revision. Correcting one elemen
For years, Swift was perceived mainly as a UI language tied to Apple client devices. With the release of Swift 6 and strict concurrency checking, Swift has matured into a premier systems with cloud en
arXiv:2609.39567v1 Announce Type: new Abstract: Spherical harmonic descriptors of closed 3D shapes depend on the parameterization, the pose and the scale of the surface, and the standard rotation-inva
arXiv:2603.06281v3 Announce Type: replace Abstract: Generative zero-shot learning (ZSL) synthesizes visual features for unseen classes by learning a semantic-conditioned generator from seen classes. S
arXiv:2609.39547v1 Announce Type: new Abstract: GUI agents built on large language and vision-language models still struggle on unseen applications and complex multi-step tasks, as completing real GUI
arXiv:2609.40219v1 Announce Type: cross Abstract: World Action Models (WAMs) couple visual dynamics prediction with action generation, yet they do not explicitly support the reuse of action experience
arXiv:2609.39723v1 Announce Type: cross Abstract: Strong unrestricted adversarial attacks can distort the primary object of an image, hereafter referred to as the subject. To preserve subject integrit
arXiv:2609.40222v1 Announce Type: new Abstract: When a camera revisits a previously observed region, a video world model should reproduce what was there before. This requires both remembering past obs
arXiv:2609.40079v1 Announce Type: cross Abstract: While recent Multimodal Large Language Models (MLLMs) have shown promise in affective computing, their reasoning capabilities are largely confined to
arXiv:2609.38278v1 Announce Type: new Abstract: Self-supervised learning (SSL) removes the need for annotations and makes models that are capable across more domains than supervised learning. The auto
arXiv:2609.39765v1 Announce Type: new Abstract: Agent memory faces heterogeneous access needs: a single-hop question may require one piece of evidence, whereas a multi-hop question must combine eviden
arXiv:2609.38392v1 Announce Type: new Abstract: Personas used to seed LLM social simulations face a cold-start problem: existing methods lack a principled basis for deciding which attributes to includ
arXiv:2609.38587v1 Announce Type: new Abstract: Electroencephalography (EEG) is recorded continuously over hours, with relevant dynamics spanning timescales from milliseconds to hours. Most EEG founda
arXiv:2609.39346v1 Announce Type: new Abstract: Large language models (LLMs) offer strong reasoning capabilities but are often costly to access through commercial APIs, while small language models (SL
arXiv:2609.38490v1 Announce Type: cross Abstract: Large language model (LLM) agents that reason over clinical records must track changes in a patient's state while preserving the history needed to und
arXiv:2609.40358v1 Announce Type: new Abstract: Video world models are expected to predict how the physical world evolves, yet they often produce visually plausible videos that violate basic physical
arXiv:2609.38458v1 Announce Type: new Abstract: Clinical large language model (LLM) agents deployed locally can consult more capable remote models, but doing so risks exposing patient information. Pri
arXiv:2609.38593v1 Announce Type: cross Abstract: Skills are external artifacts that Large Language Models (LLMs) consume at inference time to improve their performance on specialized domains by incor
I put an old RTX 3090 to work as a local coding agent with Qwen3.8-27B, llama.cpp, and OpenCode. Here are the setup and results, including what failed. This is a summary of my own blog post, linked be
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:2602.08005v2 Announce Type: replace-cross Abstract: Efficient long-context inference faces two coupled bottlenecks: KV-cache memory grows linearly with context length, while attention computatio
arXiv:2609.39929v1 Announce Type: cross Abstract: Long-context failures of RoPE-based language models can arise from RoPE's intrinsic tradeoff between maintaining stable token preferences and distingu
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:2609.39688v1 Announce Type: cross Abstract: Multimodal encoders such as CLIP underlie many downstream systems, but their web-scale training data embed harmful associations that safety alignment
arXiv:2609.38881v1 Announce Type: new Abstract: Real-time strategy (RTS) games require agents to coordinate economic development, production and construction, base defense, unit organization, and atta
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:2609.39578v1 Announce Type: new Abstract: Agent harnesses often improve language models with human-designed workflows, but as models grow more capable, unreliable guidance can increasingly const
arXiv:2609.39051v1 Announce Type: new Abstract: Existing multimodal video highlight detectors typically assume that visual, audio, and textual streams are continuously available. In practice, however,
arXiv:2609.38275v1 Announce Type: cross Abstract: Persistent memory helps LLM agents carry information across long interactions, but correct memory can still be used incorrectly when queries change or
arXiv:2609.39325v1 Announce Type: new Abstract: The ability of Large Language Model (LLM) agents to complete daily and professional work is receiving increasing attention. Training such agents require
arXiv:2609.32472v2 Announce Type: replace Abstract: Document rerankers determine what evidence reaches the downstream model in RAG and deep research, yet mainstream rerankers select by relevance match
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:2609.37616v1 Announce Type: cross Abstract: Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on t
arXiv:2512.07011v2 Announce Type: replace-cross Abstract: Modern large language models increasingly require long contexts for reasoning and multi-document tasks, but attention's quadratic complexity c
arXiv:2609.32192v2 Announce Type: replace Abstract: Multi-agent workflows require task-relevant information to be shared across agents, while irrelevant, stale, unverified, or incompatible information
arXiv:2609.37458v1 Announce Type: new Abstract: Industrial standards often encode the same engineering concept through incompatible hierarchies, identifiers, roles, and structural constraints, so the
arXiv:2609.36259v1 Announce Type: new Abstract: Linear RNNs offer linear-time sequence processing and constant-memory decoding, but their fixed-size recurrent states must accommodate all past key--val
arXiv:2609.36753v1 Announce Type: new Abstract: Autonomous robot navigation relies on simultaneous localization and mapping (SLAM) to estimate motion and maintain an accurate pose within an environmen
arXiv:2609.37472v1 Announce Type: cross Abstract: Behavioral tests measure how a language model reads evidence. We ask whether those measurements help choose a recommendation interface. We evaluate si
arXiv:2609.37923v1 Announce Type: new Abstract: Agents can learn from past executions, but enabling different agents to reuse and build on one another's experience remains challenging. We introduce Ep
arXiv:2609.36952v1 Announce Type: cross Abstract: Large language models (LLMs) excel at token-level generation but may learn undesirable abstract semantics and lack comprehensive perception. LLM-JEPA
arXiv:2609.36458v1 Announce Type: cross Abstract: Semantic-preserving transformations can induce substantial motion in learned representations, while small changes may strongly affect model prediction
arXiv:2609.37314v1 Announce Type: new Abstract: Synthetic anomaly generation helps expand industrial anomaly datasets when real defects are scarce or unavailable. Existing approaches lie at two extrem
arXiv:2609.36082v1 Announce Type: new Abstract: We introduce GeoOutageBench, a benchmark for assessing LLM-based geospatiotemporal KGQA for multimodal outage and resilience analysis. Unlike existing K