Knowledge catalogue
arXiv:2608.26336v1 Announce Type: cross Abstract: Recent advancements in generative models are pushing video generation toward unbounded streaming audio-video generation for real-time interactive worl
arXiv:2608.27128v1 Announce Type: new Abstract: Long-context inference is bottlenecked by the memory footprint of the key-value (KV) cache, especially for small models under tight resource budgets. Ex
arXiv:2510.25732v2 Announce Type: replace-cross Abstract: Unlearning in large language models (LLMs) is usually evaluated as whether an 'unlearned' fact can be recovered. We instead ask whether a fact
arXiv:2512.21852v4 Announce Type: replace Abstract: The reasoning performance of large language models (LLMs) can be substantially improved by training them with reinforcement learning (RL). The RL ob
arXiv:2608.25489v1 Announce Type: cross Abstract: Graph retrieval-augmented generation places retrieved subgraphs into the model's context window at query time, paying a recurring token cost and expos
arXiv:2509.06346v3 Announce Type: replace Abstract: Sparse Mixture-of-Experts (MoE) has become a key architecture for scaling large language models (LLMs) efficiently. Recent fine-grained MoE designs
arXiv:2608.25500v1 Announce Type: cross Abstract: Reusable skill libraries allow large language model (LLM) agents to reuse procedural knowledge across tasks, but they also turn memory access into a c
arXiv:2608.24945v1 Announce Type: new Abstract: Recent years have witnessed remarkable achievements of Large Language Models (LLMs) in multiple domains, while the excessive resource requirements of LL
arXiv:2608.25894v1 Announce Type: new Abstract: Large language models (LLMs) frequently produce confident yet factually incorrect responses when user inputs contain misleading premises, a phenomenon w
arXiv:2601.13207v2 Announce Type: replace Abstract: Geo-localization aims to infer the geographic location where an image was captured using observable visual evidence. Traditional methods achieve imp
arXiv:2608.25646v1 Announce Type: new Abstract: Portable electronic-nose systems based on low-cost metal-oxide (MOX) gas sensors offer a practical solution for gas and odour recognition, but their sig
arXiv:2608.25677v1 Announce Type: new Abstract: Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters. We show that
arXiv:2608.25575v1 Announce Type: new Abstract: Pretrained vision-language models such as CLIP excel at zero-shot recognition but often fail at compositionality, particularly attribute-object and rela
Since Qwen's dropped the Qwen4Exp architecture bomb that focus on offloading parameters to n-gram instead of pure mixture of experts, I dug into this and learned quite a lot. Here's the summary. Expec
arXiv:2608.25038v1 Announce Type: new Abstract: We introduce grounded glossary generation, a structured task requiring models to recover semantically meaningful Sanskrit phrases and produce translatio
arXiv:2608.25336v1 Announce Type: new Abstract: Large language models (LLMs) can fluently verbalize statistical evidence, yet statistical reports can still drift numerical values, invert effect direct
arXiv:2602.17281v2 Announce Type: replace-cross Abstract: Quantum generative modeling, where the Born rule naturally defines probability distributions through measurement of parameterized quantum stat
arXiv:2608.25973v1 Announce Type: cross Abstract: Understanding instruction-following capabilities in scientific domains is essential for effectively leveraging Multimodal Large Language Models (MLLMs
arXiv:2608.26013v1 Announce Type: new Abstract: Multimodal instruction-following models require training data that is accurate, diverse, verifiable, and challenging. Existing synthesis pipelines typic
arXiv:2608.24229v1 Announce Type: cross Abstract: Quantum noise is expected to degrade quantum machine learning by driving circuits away from their noiseless implementations. Yet recent studies show m
arXiv:2608.24033v1 Announce Type: cross Abstract: Time series classification underpins applications in healthcare, sensing, and industrial monitoring. Although time series foundation models support fo
arXiv:2608.24070v1 Announce Type: new Abstract: Prohibitive computational and environmental costs impede the scalable deployment of Large Language Models (LLMs). Traditional compression techniques (sp
arXiv:2510.14249v2 Announce Type: replace-cross Abstract: Understanding and modeling the relationship between language and sound are essential for applications such as music information retrieval, tex
arXiv:2608.23706v1 Announce Type: new Abstract: A large language model (LLM) trained on synthetic limit order book (LOB) data achieves near perfect scores in generating valid sequences of LOB events.
arXiv:2608.23569v1 Announce Type: new Abstract: State-of-the-art Natural Language to SQL (NL2SQL) models report execution accuracy exceeding 89 percent on established benchmarks such as Spider and BIR
As AI takes on more complex work, business leaders face a new challenge: enabling rapid innovation using agents while protecting their margins and budgets. To get a real return on AI, financial operat
Hi all, I'm looking for the best model for a hobby project and trying to make sense of the various data I came across. I know benchmarks do not often translate to the real world, especially to your pa
Google has launched Gemini 3.5 Transcribe, a new voice‑to‑text AI model in the Gemini 3.5 branch that powers Gboard’s “Rambler” feature on Pixel 11 and is set to roll out across Google products such a
arXiv:2603.25507v2 Announce Type: replace-cross Abstract: Network Traffic Classification (NTC) increasingly relies on data-driven models, yet its practical deployment is often constrained by limited l
arXiv:2602.06268v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly integrated into clinical workflows. However, pr
arXiv:2608.24354v1 Announce Type: cross Abstract: MLLMs are increasingly deployed in user-facing applications, yet they inherit backdoor risks from the pipelines used to construct them: triggers may r
arXiv:2608.23956v1 Announce Type: new Abstract: Test-time reasoning methods such as iterative refinement, decomposition, and repeated sampling are often evaluated in isolation, making their gains diff
arXiv:2512.13979v2 Announce Type: replace Abstract: Large reasoning models achieve strong performance on diverse tasks by producing extended chains of thought. Self-reflection, the ability to review a
arXiv:2608.24810v1 Announce Type: new Abstract: Recent work has applied Mamba style state space models (SSMs) to video anomaly detection, yet existing approaches still rely on buffering clips or windo
arXiv:2608.23635v1 Announce Type: cross Abstract: Large language models (LLMs) rely on tool calling as a fundamental agent capability, enabling them to invoke external systems and complete tasks beyon
Want to test how good GLM-5.3-Flash is? I have been finding it useful for visual explainers using /eli5. Try it with Pi or Hermes Agent in our new agent playground: https://academy.dair.ai/dashboard/p
arXiv:2608.24044v1 Announce Type: new Abstract: Latent world models plan by predicting how candidate actions transform learned representations. In self-predictive models, however, the encoder and pred
arXiv:2603.29902v2 Announce Type: replace Abstract: Interleaved text-and-image generation represents a significant frontier for Multimodal Large Language Models (MLLMs), offering a more intuitive way
arXiv:2608.21693v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) LLMs scale model capacity efficiently through sparse activation, but their large expert parameter footprint, routing imbalance,
arXiv:2608.22830v1 Announce Type: new Abstract: Deploying LLMs for enterprise Text-to-SQL is bottlenecked less by the model than by what context reaches it: business logic spans thousands of tables, a
arXiv:2509.12811v2 Announce Type: replace Abstract: Large Language Models (LLMs) have shown remarkable prowess in text generation, yet producing long-form, factual documents grounded in extensive exte
arXiv:2409.19616v3 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have proven effective in various medical imaging applications, such as automated disease diagnosis. However, due to the
arXiv:2509.10041v2 Announce Type: replace Abstract: Federated learning (FL) enables collaborative model training without centralizing data, but exchanging high-dimensional updates can expose sensitive
arXiv:2608.21754v1 Announce Type: new Abstract: Despite the success of data pruning (DP) in reducing training data sizes and improving downstream model performance in classification and segmentation t
arXiv:2606.16151v2 Announce Type: replace Abstract: Many reasoning tasks require models to reason over input context, from document-grounded question answering to rule-based deduction. Chain-of-Though
arXiv:2608.21792v1 Announce Type: new Abstract: Document classification in regulated industries is constrained by data residency, limited cold-start labels, scarce review capacity, and costly model-go
arXiv:2608.23058v1 Announce Type: new Abstract: Large language models (LLMs) now support forecasting systems that combine language-based reasoning with temporal data, evidence retrieval, external tool
I’ve been going back and forth on this for a week and I can’t settle it, so I’m hoping someone here has hands-on numbers. The two configs (German prices, dealer quote, incl. VAT): Config Price Mac Stu
Few professions are as exacting as the practice of law. A team reviewing a contract or building a case works inside strictly privileged information, firm-specific playbooks, and a body of law that cha
arXiv:2608.22637v1 Announce Type: new Abstract: Recent vision-language models (VLMs) show strong capabilities in robotic perception and spatial reasoning, yet their ability to reason about complex mec
arXiv:2608.23028v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in education, healthcare, policy advising, and other interactive settings, where users engage the
arXiv:2608.23048v1 Announce Type: new Abstract: Semi-structured N:M sparsity has emerged as a practical direction for accelerating large language models (LLMs). However, existing learnable-mask approa
arXiv:2608.21494v1 Announce Type: cross Abstract: Recent works have highlighted the expressive limitations of embedding based retrieval models through both theoretical analyses and challenging benchma
arXiv:2608.22390v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong potential in graphical user interface (GUI) generation, but reliable evaluation remains challengin
arXiv:2608.23067v1 Announce Type: new Abstract: Agent Skills are reusable procedural modules that are increasingly injected into coding-agent sessions to encode framework conventions, anti-patterns, a
arXiv:2608.22821v1 Announce Type: new Abstract: We present SiZeUp, a fast and scalable approach for constructing large-scale 3D urban proxy models directly from calibrated oblique aerial imagery. Our
arXiv:2608.22301v1 Announce Type: cross Abstract: Humans imitate at the level of intent: given a demonstration, we infer its goal and carry it out with whatever tools, objects, and layouts are at hand
arXiv:2608.23329v1 Announce Type: cross Abstract: Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video an
arXiv:2608.22504v1 Announce Type: new Abstract: Existing AI-for-PDE benchmarks primarily assess models in terms of predictive or approximation accuracy. In physics research, however, AI outputs often
arXiv:2608.22758v1 Announce Type: cross Abstract: Standard decoding rules for autoregressive language models promote diversity by rescaling the full next-token distribution or truncating its low-proba