Knowledge catalogue
arXiv:2609.32041v1 Announce Type: new Abstract: Modern Document AI reads contracts, extracts fields, reasons over tables, and grounds answers to page regions, then forgets everything. Processing an am
arXiv:2609.35521v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) expose features that help us understand and steer language models, but faithful reconstruction does not guarantee informati
arXiv:2609.32663v1 Announce Type: new Abstract: The memory usage and decoding latency of LLM inference grow rapidly with context length. To reduce these costs, key-value (KV) cache compression methods
arXiv:2609.35431v1 Announce Type: new Abstract: This paper studies low-altitude question answering (LAQA), in which distributed unmanned aerial vehicle (UAV) memories are aggregated at a ground server
arXiv:2609.34220v1 Announce Type: cross Abstract: Assistive robots increasingly operate in many human-centered environments and perform various human-robot interaction (HRI) tasks, such as object deli
arXiv:2609.34314v1 Announce Type: new Abstract: Video-language models are increasingly used as judges of video understanding, both for evaluating model outputs and for training reward models. Whether
arXiv:2609.34842v1 Announce Type: new Abstract: Existing multimodal time series foundation models (TSFMs) typically model heterogeneous modalities through largely shared mechanisms, overlooking the di
arXiv:2609.33304v1 Announce Type: new Abstract: Personal Graphical User Interface (GUI) agents rely on interaction history to infer what a user wants from ambiguous instructions and to anticipate recu
arXiv:2609.33203v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have established themselves as a scalable backbone for high-fidelity image synthesis. However, unlike U-Net based diffusio
arXiv:2609.32898v1 Announce Type: new Abstract: Pretrained tabular foundation models process every dataset at a fixed depth, with inference costs growing with dataset size. To address this, we present
arXiv:2609.30813v1 Announce Type: new Abstract: Evaluating claim admission in shared agent memory is challenging because repeated claims may be mistaken for independent evidence. An agent may copy or
arXiv:2609.31482v1 Announce Type: new Abstract: Generative AI is reshaping the cultural infrastructures through which knowledge is found, synthesized, and held accountable. To make sense of this shift
arXiv:2609.31038v1 Announce Type: new Abstract: Time series foundation models (TSFMs) enable cross-domain forecasting, but their development as general-purpose forecasters remains constrained by under
arXiv:2609.30541v1 Announce Type: new Abstract: Optimizing embedding systems for production recommendation pipelines demands systematic exploration that consumes disproportionate engineering effort at
arXiv:2609.30738v1 Announce Type: new Abstract: KV cache eviction methods such as SnapKV and PyramidKV rank tokens solely by mean attention over a small observation window. We study a unified score, m
arXiv:2609.31381v1 Announce Type: new Abstract: Context projection replaces older tool observations with compact, addressable excerpts, reducing repeated input while potentially adding evidence-retrie
arXiv:2609.31568v1 Announce Type: new Abstract: AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Clou
arXiv:2609.30882v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to assess long-form medical videos, but their effectiveness may depend on whether transcripts are pro
arXiv:2609.30867v1 Announce Type: new Abstract: Difference-in-differences (DID) studies are widely used to evaluate climate policy, but assessing the evidence supporting their identification assumptio
arXiv:2609.31397v1 Announce Type: cross Abstract: Automated and highly usable Quality-of-Service (QoS) enforcement requires translating high-level service intents into deployable traffic-management po
arXiv:2609.31045v1 Announce Type: cross Abstract: Conversational agents, generative recommenders, and personalized advertising all rest on one capability: understanding each user from raw behavior. Pr
arXiv:2609.30706v1 Announce Type: new Abstract: 'System One' decision models such as TypeSafe's Jev and its open counterpart Laya answer typed questions about a text in a single forward pass with cali
arXiv:2609.30547v1 Announce Type: new Abstract: Audience sizing is a critical component of digital marketing. It enables precise resource allocation, campaign planning, and performance optimization. T
arXiv:2609.30705v1 Announce Type: new Abstract: While inference-time reasoning in large language models (LLMs) promises better decision making, its higher computational cost may not yield better econo
arXiv:2609.30761v1 Announce Type: new Abstract: Most existing human motion generation (HMG) methods use cross-attention modules to inject text semantics, but ignore the importance of bidirectional mod
arXiv:2609.30670v1 Announce Type: new Abstract: Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often report task scores without specifying w
arXiv:2609.31005v1 Announce Type: new Abstract: Open-vocabulary 3D maps enable robots to reason about previously unknown environments using natural language. However, existing systems typically segmen
arXiv:2609.31448v1 Announce Type: cross Abstract: Clinical prediction models estimate risk from patient measurements, while large language models support medical text understanding and question answer
arXiv:2609.30402v1 Announce Type: cross Abstract: Multimodal misinformation is increasingly crafted to look convincing by pairing a textual claim with an image that appears to 'prove' it. Yet in pract
arXiv:2609.30328v1 Announce Type: new Abstract: When one language model judges whether another's code is correct, it does not report the absence of evidence. It returns a confident verdict with reason
arXiv:2609.30716v1 Announce Type: cross Abstract: When a language model receives two conflicting documents as input, how does it decide which one to prioritize? Does it rely on how the sources are fra
Banger paper from Salesforce AI Research on agent memory. The overall finding is that you want to store raw trajectories and decide what to extract from them when the next task arrives, instead of sum
arXiv:2609.30036v1 Announce Type: new Abstract: Planners built on visual world models commonly score each predicted outcome by its distance to the encoded goal image. We show that this target can limi
arXiv:2609.28524v1 Announce Type: cross Abstract: Magnetic resonance imaging and histopathology observe the same glioma at radically different scales. We present CrossScale-GLIO, a visual multimodal f
arXiv:2609.29329v1 Announce Type: cross Abstract: Existing continual-learning methods protect parameters, replayed examples, or Euclidean feature subspaces. When applied to hyperbolic multimodal model
arXiv:2602.08329v2 Announce Type: replace-cross Abstract: A core bottleneck in large language model (LLM) inference is the cost of attending over the ever-growing key-value (KV) cache. Although near-o
Compute (EC2) opened the front door to the first generation cloud. Agents need something different: compute, inference, and data working as one. We built the cloud that delivers all three as one simpl
arXiv:2507.00938v4 Announce Type: replace-cross Abstract: Foundation models now enable autonomous agents to interact with real-world websites, but existing benchmarks emphasize general-purpose browsin
Entire database engineering careers have been spent on a single question: How do you scale an OLTP workload without compromising the system of record that owns the data? Exadata answered the question
In this episode of The Agent Factory, we explore the reality of building with autonomous agents alongside Ryan Lopopolo, a software engineer at Google Cloud and the person who coined the term agent ha
arXiv:2609.26828v1 Announce Type: cross Abstract: NAND-backed storage offers the capacity needed to scale LLM prefix caching, but its block I/O path incurs CPU cache contention and host-DRAM staging i
arXiv:2609.27749v1 Announce Type: new Abstract: The surge in AI-assisted generation of educational materials has outpaced our capacity to validate their pedagogical quality. Automated evaluation using
arXiv:2609.27334v1 Announce Type: new Abstract: Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory at write time: once a task is comple
arXiv:2609.28086v1 Announce Type: cross Abstract: We propose LAYERSCOPE, a label-free, layerwise framework that aims to characterize a model's learned representations in video and multimodal settings.
arXiv:2609.28003v1 Announce Type: new Abstract: Small and medium-sized language models offer cost-effective executors for tool-using agents, making them attractive for local and large-scale deployment
arXiv:2609.27009v1 Announce Type: new Abstract: Large language models are increasingly applied to high-risk domains such as law, yet complex legal reasoning remains limited by two structural challenge
Introduction The landscape of software supply chain security has undergone a significant shift. Recent campaigns demonstrate that sophisticated threat actors are systematically targeting the engineeri
arXiv:2609.27612v1 Announce Type: new Abstract: Long-horizon robot execution requires a clear distinction between a model's proposal, a controller's termination, and verified task completion. We prese
arXiv:2609.27671v1 Announce Type: new Abstract: 4D radar complements dense image semantics with long-range geometry and radial motion, but existing radar--camera detectors largely solve where to align
arXiv:2609.27332v1 Announce Type: new Abstract: Long horizon agents accumulate growing interaction histories that increase context and inference costs. We find that geometric redundancy alone is an in
arXiv:2609.27277v1 Announce Type: new Abstract: Time series agents answer analytical questions by calling external tools, and which tools they carry is decided by people before the agent runs. However
arXiv:2609.27037v1 Announce Type: new Abstract: Wake word detection is a critical component of virtual assistants, serving as the gateway to seamless user interactions. This paper introduces a novel w
arXiv:2609.26502v1 Announce Type: cross Abstract: Deep generative models are widely reported to enable de novo crystal structure prediction (CSP), but their capability has not been measured consistent
arXiv:2609.25055v1 Announce Type: new Abstract: In this report we present results of the ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains. This competition aimed to adv
arXiv:2609.26257v1 Announce Type: new Abstract: Continual learning (CL) aims to incrementally acquire knowledge from sequential data while avoiding catastrophic forgetting. Recently, prompt tuning has
arXiv:2609.25331v1 Announce Type: new Abstract: Low-light image enhancement (LLIE) is an im- portant component of visual sensing systems operating under degraded illumination, including nighttime surv
arXiv:2609.23539v1 Announce Type: cross Abstract: Agents may need capabilities exposed through external agent endpoints or service APIs. When a requester is not already bound to a provider, it must di
arXiv:2609.22939v1 Announce Type: cross Abstract: Long-context models read a novel the way a person reads a printout: one token after another, in narrative order, with the whole history competing for
arXiv:2609.22641v1 Announce Type: new Abstract: Autoregressive video world models enable temporally coherent generation for a single observer. Extending them to multiple agents requires consistency ac
arXiv:2609.22104v1 Announce Type: new Abstract: As automated scientific discovery advances, Large Language Models (LLMs) can now generate research ideas at an unprecedented scale, shifting the bottlen