Knowledge catalogue
Alibaba has released Qwen Audio 3.0 Realtime, with the Plus variant debuting as the new #1 model on the Artificial Analysis Speech to Speech Index at 84.1%, ahead of GPT-Realtime-2.1 High at 79.1% Rel
arXiv:2607.23219v1 Announce Type: new Abstract: Machine learning interatomic potentials (MLIPs) approximate quantum-mechanical energies and forces---conventionally computed by density functional theor
arXiv:2607.22910v1 Announce Type: new Abstract: Pearl's structural causal model (SCM) framework, built on directed acyclic graphs (DAGs) and the do-calculus, is the dominant formal language for causal
Increasing the adoption of generative AI across the enterprise requires you to do more than deploy a generic chatbot with a custom wrapper. Interacting with business-critical databases demands absolut
arXiv:2607.22948v1 Announce Type: cross Abstract: The ORBIT (Operations Responses and Business Intelligence Toolkit) project was initiated to assess agentic AI for the upcoming ESnet 7 initiative and
arXiv:2607.24236v1 Announce Type: new Abstract: Long-form question answering increasingly relies on retrieved evidence to make LLM outputs verifiable, with inline citations tracing claims to source do
arXiv:2603.24714v2 Announce Type: replace Abstract: Analog design often slows down because even small changes to device sizes or biases require expensive simulation cycles, and high-quality solutions
arXiv:2607.23507v1 Announce Type: cross Abstract: Choosing the right text embedding model is one of the most consequential -- and most frequently under-examined -- decisions in building a retrieval or
arXiv:2607.23693v1 Announce Type: new Abstract: Long-horizon agents increasingly reuse their KV cache as memory: a serving system keeps a subset of cached entries and drops the rest. Eviction and epis
arXiv:2607.23835v1 Announce Type: new Abstract: Attribution methods are widely used to characterize the evidence underlying model predictions, yet their potential to improve model behavior remains und
arXiv:2505.18334v2 Announce Type: replace-cross Abstract: Past work has demonstrated that autonomous vehicles can drive more safely if they communicate with each other. However, this communication is
arXiv:2607.22662v1 Announce Type: new Abstract: Open-web corpora curated via highly selective filters, such as FineWeb-Edu and DCLM, constitute the core of LLM pretraining data and have significantly
arXiv:2607.24016v1 Announce Type: new Abstract: Recent advances in generative models have shifted AI-generated image detection from identifying easily distinguishable, fully synthetic images to identi
arXiv:2607.22718v1 Announce Type: cross Abstract: We propose parameter-efficient SSM-based U-Net architectures for 3D medical image segmentation. Convolutional U-Nets afford O(n) local mixing per laye
arXiv:2607.24744v1 Announce Type: cross Abstract: Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require d
arXiv:2607.23524v1 Announce Type: new Abstract: Deep search is becoming a core capability of modern agent systems, yet it is typically evaluated solely based on end-to-end answer accuracy. This couple
arXiv:2607.22928v1 Announce Type: new Abstract: Generative UI tools promise to democratize UI design by turning natural language descriptions into complete interfaces. Alongside the interface, these t
arXiv:2607.22880v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have driven growing interest in using LLMs to automate test generation. Prior work commonly evaluates
arXiv:2607.24560v1 Announce Type: cross Abstract: We introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams, obtained by fine-tuning a pretrained V2V diffusion transformer
arXiv:2607.24449v1 Announce Type: cross Abstract: International recruitment in France requires navigating a layered legal framework absent from existing legal AI benchmarks. We present a publicly avai
arXiv:2607.22655v1 Announce Type: new Abstract: Estimating origin-destination (OD) flows under disruptive events is important for disaster response and urban resilience. Existing deep OD models traine
arXiv:2607.23955v1 Announce Type: new Abstract: Reinforcement learning enables Agentic RAG systems to learn multi-turn search from verifiable outcome rewards, but all- zero rollout groups provide no c
arXiv:2607.24177v1 Announce Type: cross Abstract: Due to the lack of systematic evaluations, we are not yet able to determine which AI-based Windows malware detector to deploy in production, since exi
arXiv:2607.23636v1 Announce Type: cross Abstract: Data profiling aims to extract complex patterns from data for further analysis and use that data in domains such as data cleaning, data deduplication,
arXiv:2607.23682v1 Announce Type: new Abstract: Early warning of extreme market volatility is central to financial risk management, but actionable events are rare, nonstationary, and often triggered b
arXiv:2607.24167v1 Announce Type: new Abstract: Long-horizon web agents often go off track before final failure: a trajectory can remain locally plausible even after the current state, reused skill, o
arXiv:2506.03168v2 Announce Type: replace Abstract: Amid the challenges posed by global population growth and climate change, traditional agricultural Internet of Things (IoT) systems is currently und
arXiv:2607.24207v1 Announce Type: new Abstract: Mobile manipulation requires robots to identify Floor Affordance (FloAff) that maximizes downstream manipulation success rather than merely ensuring nav
arXiv:2607.22837v1 Announce Type: cross Abstract: Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns
arXiv:2607.22847v1 Announce Type: new Abstract: Human gaze does more than point to visual targets; it serves as a subtle indicator of social intent within static images, whereas standard models typica
arXiv:2607.23917v1 Announce Type: new Abstract: We introduce a novel learning problem: decoding gaze into natural language descriptions of human goals across diverse visual tasks. Unlike prior work, w
arXiv:2512.16275v2 Announce Type: replace-cross Abstract: Automated floor plan generation lies at the intersection of combinatorial search, geometric constraint satisfaction, and functional design req
hi everyone, im a masters student at Edinburgh Napier University and im conducting research on how Generative AI tools are being taken up across professional services (accounting, audit, law, tax and
Most quantization works like this: pick a bit depth, apply it everywhere, maybe let imatrix take a rough guess at what matters, ship it. Most don't check which specific weight groups can take a hit an
arXiv:2607.22683v1 Announce Type: new Abstract: With the unprecedented success of Language Models (LMs), the science of Prompt Engineering has evolved the powerful idea of Prompt Programming, where pr
arXiv:2607.23394v1 Announce Type: new Abstract: Recent work shows that fine-tuning language models on even a small amount of poisoned data can install targeted misbehavior, and ostensibly benign data
arXiv:2601.05680v2 Announce Type: replace-cross Abstract: While Transformer-based autoregressive models excel in data generation, their token discretization strategy inherently limits their precision
arXiv:2606.22916v2 Announce Type: replace Abstract: AI agents increasingly act through external tools: they read private data, construct structured payloads, submit write requests, export records, and
arXiv:2510.17944v2 Announce Type: replace-cross Abstract: In this paper, we generalize Pearl's do-calculus to an Intuitionistic setting called j-stable causal inference inside a topos of sheaves. Our
arXiv:2607.22944v1 Announce Type: cross Abstract: Invariants, the relations expected to hold among measured signals of a network, underpin applications from verification to traffic generation, telemet
Been running a GPU price tracker (https://www.pricesquirrel.com) since March, covering 20+ EU stores, recently added RAM, SSDs and CPUs too. Every GPU tier has gotten cheaper since launch. The RTX 509
I've been digging into Krea2 to see if there's any way to condition inference in specific regions of pixel -> latent space to implement bbox type prompting in order to apply multiple simultaneous char
arXiv:2607.24260v1 Announce Type: new Abstract: Modern LLM systems increasingly rely on knowledge-selection processes that produce high-value structured priors, such as ranked evidence, graph topology
arXiv:2607.22924v1 Announce Type: new Abstract: In the real world, fashion is about layering: adding a jacket over a shirt, or a sequence of adding and removing layers, rather than just a single-layer
arXiv:2607.22690v1 Announce Type: new Abstract: Long-term memory lets LLM agents reuse past interactions, but raw dialogue histories are verbose and information-sparse. Retrieving broadly improves evi
arXiv:2607.24435v1 Announce Type: cross Abstract: Large language models may easily assign personality labels from text, but model interpretability remains an open problem. To address this gap, we intr
LFM2.5-Encoder is a family of multilingual bidirectional encoders built on the LFM2 architecture, available in two sizes: LFM2.5-Encoder-230M — a lightweight encoder for tight latency and memory budge
arXiv:2607.24555v1 Announce Type: cross Abstract: Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step. Attention keys
arXiv:2607.23204v1 Announce Type: cross Abstract: Large language model (LLM)-based dialogue systems suffer response delays because generation begins only after final speech recognition. While fixed fi
arXiv:2607.24097v1 Announce Type: new Abstract: Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model. This retrieval-as-evi
arXiv:2607.23504v1 Announce Type: new Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to maintain long-horizon visual history for trajectory consistency wh
arXiv:2607.22556v1 Announce Type: new Abstract: Continual learning (CL) is essential for small language models (SLMs) to adapt to evolving real-world needs in resource-constrained deployments. However
arXiv:2607.24256v1 Announce Type: cross Abstract: As communication networks adopt virtualized and disaggregated architectures, achieving energy efficiency has become increasingly important for both ec
arXiv:2607.22586v1 Announce Type: new Abstract: Key-Value (KV) caching is essential for efficient inference in multimodal large language models (MLLMs), yet its memory footprint grows linearly with co
Hey guys, I am so excited to share this with you guys. I know for a lot of Pros here, this maybe a baby's work so please be gentle. Until a month ago, I didnt know anything but to use those google AI
New research from Meta and CMU. This one is on agentic context management for long horizon tasks. (bookmark it) Production agents accumulate context every turn. The usual fix compresses on a token thr
arXiv:2607.24190v1 Announce Type: cross Abstract: Social robots that rely on large language models for conversation are unable to retain information across sessions. This absence of memory violates so
arXiv:2607.22738v1 Announce Type: cross Abstract: Current 3D generative models mostly produce a final surface: a visually strong but largely opaque mesh. Interactive 3D worlds need more than a surface
arXiv:2509.02594v3 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on their ability to generate high-quality, accurate, situationally aware answers to clinical questions
arXiv:2607.18553v2 Announce Type: replace-cross Abstract: Can a language model read the quality of its ongoing computation, and can an external intervention turn that readout into better outcomes? We