Knowledge catalogue
arXiv:2603.14377v2 Announce Type: replace Abstract: Prevailing High Dynamic Range (HDR) video reconstruction methods are fundamentally trapped in a fragile alignment-and-fusion paradigm. While explici
arXiv:2606.03910v1 Announce Type: cross Abstract: Disaggregated LLM inference forces the KV cache to traverse the datacenter network before decoding begins, so transfer time enters directly into the T
arXiv:2606.02877v1 Announce Type: new Abstract: Integrating transcriptomics and histopathology can improve cancer risk modelling, yet practical use is constrained by the limited availability of RNA pr
arXiv:2606.03598v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved remarkable success in language-conditioned robotic manipulation. However, deploying these models in
arXiv:2606.03057v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for molecular tasks, but it remains unclear which molecular representation to use. We present a sys
arXiv:2606.02951v1 Announce Type: cross Abstract: Deploying language-driven agents in robotics requires evaluations that reflect real-world task demands: natural-language instructions with reproducibl
Two bits here I think we're going to see a lot more: 1. custom harnesses / finetunes on smaller open source models to beat frontier models at specific skill or task 2. using frontier models as critics
arXiv:2606.02908v1 Announce Type: cross Abstract: Multi-turn user-facing agents must infer user intent from incomplete requests, collect missing information through dialogue and tools, and execute val
arXiv:2606.00550v1 Announce Type: cross Abstract: The persistent challenge in scaling authentic manipulator education within university laboratories is a structural dichotomy: commercial digital twins
arXiv:2606.01104v1 Announce Type: new Abstract: VRR-QA evaluates whether video-language systems can infer spatial, temporal, viewpoint, depth, and visibility relations that are not always resolved by
arXiv:2606.01279v1 Announce Type: new Abstract: AI agents are increasingly being tasked with automating AI research itself, particularly the critical post-training phase that transforms base LLMs into
arXiv:2606.00130v1 Announce Type: cross Abstract: We study Automatically Differentiable Nonlinear Tensor Networks (ADNTNs), a family of structured weight generators whose compact core tensors are trai
arXiv:2606.00712v1 Announce Type: new Abstract: The CASTLE Challenge @ EgoVis 2026 evaluates long-form egocentric video question answering over 600+ hours of multi-perspective recordings. Each four-ch
arXiv:2606.00837v1 Announce Type: cross Abstract: Diffusion models provide strong priors for generating structured data, but many tasks require outputs beyond the scale on which these models are typic
arXiv:2606.00101v1 Announce Type: cross Abstract: With the rapid advancement of artificial intelligence generated content (AIGC) technologies, video forgery has become increasingly prevalent, posing n
arXiv:2606.00658v1 Announce Type: cross Abstract: Large video diffusion models achieve strong visual quality but remain expensive to deploy because each sample requires many denoising steps and a larg
arXiv:2606.00761v1 Announce Type: cross Abstract: SwiGLU has become a standard gated activation in modern Transformer MLPs, yet its gate sharpness -- the smoothness and selectivity of the gating funct
arXiv:2606.00315v1 Announce Type: new Abstract: Modern generative machine learning (ML) models can propose novel inorganic crystalline materials with targeted properties; however, synthesis planning o
arXiv:2606.02204v1 Announce Type: new Abstract: Large language model agents achieve strong performance on text-based benchmarks but incur prohibitive inference costs, motivating the use of compact neu
arXiv:2606.00931v1 Announce Type: cross Abstract: Instruction-guided image editing is becoming a general interface for visual work, yet existing benchmarks still focus largely on narrow appearance edi
arXiv:2606.01062v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effe
arXiv:2606.01162v1 Announce Type: new Abstract: Workflow scheduling in cloud computing demands the intelligent allocation of dynamically arriving, graph-structured workflows with varying deadlines ont
arXiv:2606.00435v1 Announce Type: cross Abstract: Vision-language models (VLMs) can produce confident visual answers even when the required visual evidence is missing, blank, or unrelated to the quest
arXiv:2606.01666v1 Announce Type: cross Abstract: The scaling of Large Language Models (LLMs) has driven significant performance gains but created substantial challenges in inference efficiency. While
arXiv:2606.01909v1 Announce Type: cross Abstract: We present Echo, a proof-of-concept audio system built around a single 25 M-parameter ViT encoder. The encoder is pretrained with a JEPA objective and
arXiv:2606.02049v1 Announce Type: new Abstract: The increasing integration of renewable energy sources into power systems, particularly in buildings equipped with photovoltaic (PV) panels and energy s
arXiv:2604.03893v2 Announce Type: replace Abstract: Current multimodal benchmarks for scientific reasoning primarily evaluate local information extraction -- models recognize symbols and values and th
arXiv:2606.00301v1 Announce Type: new Abstract: Hallucinations in large language models (LLMs) arise from heterogeneous failure mechanisms, making reliable detection difficult for any single global un
arXiv:2606.02424v1 Announce Type: cross Abstract: Histology-based single-cell spatial transcriptomics (ST) estimation aims to predict gene expression for individual cells from histopathological images
arXiv:2606.01822v1 Announce Type: new Abstract: Traffic sign detection is a fundamental component of environmental perception in autonomous driving and intelligent transportation systems. However, mos
If your daughter needs tutoring in algebra, you can probably find someone cheaper than Albert Einstein. Giving every task to GPT5.5 or Opus 4.8 is overkill. Often times you can get the task done just
arXiv:2606.00520v1 Announce Type: cross Abstract: Many stochastic gradient methods are believed not to converge when the noise in stochastic gradients has only a finite p-th moment for pinleft(1,2righ
arXiv:2606.01282v1 Announce Type: new Abstract: Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cu
arXiv:2606.01425v1 Announce Type: new Abstract: Mixed-combinatorial nonlinear programming (MCNLP) problems arise in many engineering design and planning applications, e.g., due to categorical, compone
arXiv:2606.00718v1 Announce Type: new Abstract: While Large Language Models (LLMs) have recently shown promise in Automated Heuristic Design (AHD), existing methods typically generate and evolve heuri
arXiv:2606.01196v1 Announce Type: cross Abstract: Safety alignment learned in high-resource languages transfers poorly to low-resource languages. Models refuse harmful prompts in English but fail to r
arXiv:2606.00285v1 Announce Type: new Abstract: Large-scale multilingual bitext often contains two distinct problems: non-parallel sentence pairs and low-quality translations. We decompose model-based
arXiv:2606.00146v1 Announce Type: cross Abstract: Motion artifacts in magnetic resonance imaging (MRI) degrade diagnostic reliability. Existing deep learning methods are typically contrast-specific an
arXiv:2606.01839v1 Announce Type: cross Abstract: LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when t
arXiv:2606.01803v1 Announce Type: new Abstract: The explosive growth of Text-to-Image (T2I) models, from large-scale versions to lightweight, real-time ones, now faces diminishing marginal returns fro
arXiv:2606.00117v1 Announce Type: new Abstract: This paper proposes ontology-guided reasoning for affordance-based explanations of robot navigation. In human environments, it is not sufficient for a r
arXiv:2606.01485v1 Announce Type: new Abstract: We describe our submission to the VRR Challenge @ CVPR 2026, built on the ImplicitQA / VRR-QA benchmark~ite{implicitqa}: multiple-choice video question
arXiv:2606.01597v1 Announce Type: new Abstract: Robot swarms can exhibit coherent collective behaviors through local perception, limited communication and decentralized decision-making, yet modeling a
arXiv:2606.02506v1 Announce Type: new Abstract: The VRR-QA challenge evaluates visual relational reasoning in videos, where answers often depend on implicit spatial relations, event boundaries, target
arXiv:2606.01613v1 Announce Type: cross Abstract: This paper presents an agentic retrieval-augmented generation (RAG) framework for domain-specific technical reasoning support, instantiated over a cur
This is actually one of the main advantages startups have over frontier labs, as long as there's a healthy spectrum of open-weight to closed-weight models on the cost-performance curve. Building a mod
arXiv:2606.02142v1 Announce Type: new Abstract: The ongoing digitization has led to a proliferation of time-series data streams that monitor a variety of processes, from which valuable insights may be
arXiv:2606.01591v1 Announce Type: new Abstract: The TimeLogic Challenge evaluates formal temporal-logic reasoning over video - 16 operators (before, after, until, since, always, co-occur, ordering, ..
arXiv:2606.02138v1 Announce Type: cross Abstract: Out of distribution (OOD) events in multivariate time series forecasting are rare but often dominate real world risk, making average case forecasting
arXiv:2606.00333v1 Announce Type: new Abstract: LLMs increasingly answer questions about taxes, labor protections, healthcare, education, pensions, and administrative procedures, where usefulness ofte
arXiv:2605.30843v1 Announce Type: new Abstract: In the forward reinforcement-learning problem, the reward is fixed and known; the learner is asked to find a good policy or value function. Here we turn
arXiv:2605.31437v1 Announce Type: new Abstract: CT interpretation requires radiologists to review hundreds of volumetric slices per examination, making reporting time-consuming and highly expertise-de
arXiv:2605.30613v1 Announce Type: cross Abstract: Over the past year, prompt caching in Large Language Models (LLMs) has become increasingly more popular across inference APIs. Prompt caching helps sa
arXiv:2605.30802v1 Announce Type: cross Abstract: Prediction markets aggregate collective intelligence to forecast uncertain events, but their utility depends on reliable outcome resolution. Existing
arXiv:2605.30771v1 Announce Type: new Abstract: AI agents that persist across sessions need memory they can retrieve, audit, update, and erase. Existing memory systems often collapse source evidence,
arXiv:2605.30486v1 Announce Type: cross Abstract: Spatio-temporal forecasting on sensor graphs is commonly tackled with a single backbone architecture applied uniformly across all nodes, although grap
arXiv:2605.31304v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are widely used, but interpreting what they actually learn remains difficult. A major obstacle is that individual neurons
arXiv:2605.31478v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to automate power-system analysis, but many utilities and energy-research labs require on-premise s
arXiv:2605.30468v1 Announce Type: new Abstract: This paper presents a learning-based navigation framework for indoor mobile robots. The proposed method combines a supervised neural global planner, tra
arXiv:2605.31201v1 Announce Type: new Abstract: Financial retrieval-augmented generation (RAG) systems typically rank evidence by textual relevance, but in financial markets the useful evidence source