Knowledge catalogue
arXiv:2511.20809v2 Announce Type: replace Abstract: We present Split-then-Merge (StM), a novel framework designed to enhance control in generative video composition and address its data scarcity probl
arXiv:2608.24795v1 Announce Type: new Abstract: Recently, the rapid advancement of multimodal domains has driven a data-centric paradigm shift in graph ML, transitioning from text-attributed to multim
Megathread for discussing the release of GLM-5.3-Flash. Quants Fine-Tunes & Abliterations Chat Templates Inference Server Support & Configuration Experiences, Benchmarks & Model Comparisons We'll try
arXiv:2608.24082v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong capabilities in table reasoning, but their effectiveness degrades as tables grow in size and complexity
arXiv:2608.24842v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as AI analysts to process financial disclosures and support AI-assisted investment decisions. Y
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:2603.00188v2 Announce Type: replace-cross Abstract: Training-free KV cache compression is essential for deploying vision-language GUI agents under memory and latency constraints, yet existing me
the coolest people are coming to talk at our conference!!!!! @howietl i first used airtable when I was an intern at Tinder 10 years ago and now Hyperagent is a bb customer @swyx a total living legend
The hottest neolabs are the application layer, who serve as an intermediary layer providing their customers the best intelligence per token per task/workflow across different underlying model provider
arXiv:2608.23705v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly capable of generating text that challenges human performance in domains requiring creativity, yet evalua
Today we’re introducing Gemini 3.5 Transcribe, our latest transcription model built for incredibly precise, smart dictation across your favorite apps and devices. Remember when traditional speech-to-t
Benchmarked qwen3.8 xhigh, medium and muse glimmer. Xhigh effort mode with qwen3.8 took almost 30hrs. (And still failed on 16 cases because of the 32K output token limit) Medium effort mode and muse g
arXiv:2608.23978v1 Announce Type: new Abstract: Visual grounding is typically evaluated as a one-shot mapping from an informative referring expression to a visual target. This formulation misses a cen
arXiv:2608.21444v1 Announce Type: new Abstract: Multi-drone systems are increasingly positioned for safety-critical missions such as search and rescue (SAR) and critical infrastructure monitoring. Yet
arXiv:2608.22617v1 Announce Type: cross Abstract: Assembly and disassembly processes rely on expert knowledge that is difficult to document, reuse, and transfer. This paper presents a data-centric app
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:2608.22101v1 Announce Type: new Abstract: Modern voice-agent systems rely on streaming speech recognition models that operate under stringent latency constraints. This study shows that, due to t
arXiv:2608.23172v1 Announce Type: new Abstract: Large-scale vision-language models (VLMs) have demonstrated remarkable versatility across a wide range of multimodal tasks. However, understanding humor
arXiv:2608.22583v1 Announce Type: cross Abstract: Clinical records contain rich evidence about patient state, but converting that evidence into reliable, structured knowledge graphs remains difficult
arXiv:2608.22819v1 Announce Type: new Abstract: Text-conditioned image-to-video (I2V) generation has advanced rapidly, yet generating videos with multiple subjects remains challenging. A model must si
arXiv:2608.22411v1 Announce Type: new Abstract: Social interaction increasingly takes place in multicultural settings, where individuals may draw on multiple cultural influences and adapt their commun
arXiv:2608.22761v1 Announce Type: cross Abstract: Large Language Models generate text autoregressively, but open-ended generation is prone to verbatim looping, in which models repeat spans already pre
arXiv:2608.21755v1 Announce Type: new Abstract: Long-horizon agents need memory that identifies relevant experience, resolves revisions, and exposes checkable provenance. We present ECHO (Embodied Con
arXiv:2608.21420v1 Announce Type: new Abstract: Thematic analysis (TA) has long been regarded as an inherently human, reflexive, and interpretive process. However, the extent to which LLM-generated TA
arXiv:2608.22883v1 Announce Type: new Abstract: Multimodal speculative decoding accelerates vision-language models by allowing a lightweight draft model to propose candidate tokens for parallel verifi
IBM has released Granite 4.2, an open‑source agentic AI model that adds native reasoning, tool use, coding instruction following and speech capabilities to enterprise agents. The suite of pre‑built mo
arXiv:2608.22310v1 Announce Type: new Abstract: Long-term memory is crucial for personalized responses and long-horizon agent interactions. Existing methods often rely on LLMs to compress or rewrite d
arXiv:2608.21868v1 Announce Type: new Abstract: Depression assessment from multimodal clinical interviews requires integrating dispersed evidence from multiple symptoms into a coherent PHQ-8 profile.
arXiv:2608.22138v1 Announce Type: new Abstract: Language models are usually judged by a single accuracy score, which does not reveal how their performance degrades as inputs are perturbed. We present
arXiv:2608.22750v1 Announce Type: new Abstract: Object-centric world models forecast future videos by evolving a set of entity slots, but the variables receiving dynamics supervision are often unconst
Protecting capital in today's markets requires immense speed and precision. A financial analyst preparing a deal memo works across licensed market data, internal models, and confidential client files.
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:2608.21381v1 Announce Type: cross Abstract: Personal intelligence is becoming a central frontier for user-facing AI agents. To be helpful in everyday life, agents must understand users across th
arXiv:2608.21853v1 Announce Type: new Abstract: Large language models are increasingly moving beyond text processing, adding support for other modalities such as images and audio. While text understan
arXiv:2608.22237v1 Announce Type: new Abstract: Long-horizon agents increasingly rely on repeated access to external artifacts, yet current reading interfaces often expose entire objects even when onl
arXiv:2608.21796v1 Announce Type: cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) aims to answer queries that necessitate reasoning over external knowledge sources beyond the visual
arXiv:2608.22725v1 Announce Type: new Abstract: Short-drama generation has grown into a large, industrialized pipeline, and as it scales from isolated shots to the episode level, visual continuity has
arXiv:2510.00279v3 Announce Type: replace-cross Abstract: Logical rule-based methods offer an interpretable approach to knowledge graph completion (KGC) by capturing compositional relationships in the
arXiv:2608.22472v1 Announce Type: new Abstract: Function calling represents the core capability of agentic large language models (LLMs). Existing research has focused on enhancing LLMs function-callin
Top open models by use case 👇 chat - Kimi K3, Qwen3.8 2.4T A95B reasoning - Kimi K3, DeepSeek V4 Pro coding agents - Kimi K3, DeepSeek V4 Flash, GLM 5.2 small + fast - Qwen3.8 27B, gpt-oss 20B mid-siz
arXiv:2608.23020v1 Announce Type: cross Abstract: Large language models (LLMs) require effective unlearning to address privacy regulations and safety concerns. However, achieving precise forgetting wi
Very interesting new work from Prime Intellect. Prime Agent is an impressive open-source self-improving harnesses. It's a harness for long-horizon agent work. A persistent IPython REPL lets the model
arXiv:2608.23507v1 Announce Type: cross Abstract: Historical people may appear under different languages, scripts, and transcription traditions, while distinct individuals may share highly similar or
arXiv:2608.22852v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows that they exhibit systematic, model-specific inve
arXiv:2608.20682v1 Announce Type: new Abstract: This paper formalizes and systematically characterizes Aristotelian Manifolds, a generalized structural framework built upon the Platonic Representation
arXiv:2608.20346v1 Announce Type: new Abstract: Speech systems used in customer-facing applications often require domain-specific language coverage. We present a synthetic Bengali speech dataset for t
Coming to Connected Stack in SF — @jerryjliu0, CEO & Co-founder of @llama_index, nominated by @GreylockVC. LlamaIndex is building document infrastructure for AI agents, with LlamaParse purpose-built f
arXiv:2608.20382v1 Announce Type: new Abstract: We introduce a new architecture design for multimodal large language models (MLLMs), Libra, capable of both multimodal understanding and generation. Lib
arXiv:2608.20372v1 Announce Type: cross Abstract: The Federal Highway Administration (FHWA) mandates that over 600,000 bridges in the United States be evaluated against the Recording and Coding Guide
arXiv:2608.21043v1 Announce Type: new Abstract: Conventional in-distribution evaluation can overestimate robustness when training and test data share recurring task-specific patterns or surface cues.
arXiv:2608.21317v1 Announce Type: new Abstract: The European Union (EU) has emerged as a leading regulatory body in the development of sustainability and privacy regulations. While new regulation requ
arXiv:2608.20761v1 Announce Type: cross Abstract: In non-stationary multivariate time series, different variables and samples often exhibit heterogeneous latent dynamic states, while existing deep for
arXiv:2608.21156v1 Announce Type: cross Abstract: LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks. This evolution has produced paradigms includin
arXiv:2608.20580v1 Announce Type: cross Abstract: Federated learning (FL) is vulnerable to multi-level attacks. However, existing methods address them separately, leaving FL exposed to data leakage, u
arXiv:2608.20557v1 Announce Type: new Abstract: Domain shift across clinical centers using different imaging hardware or acquisition protocols remains a fundamental barrier to deploying deep learning
arXiv:2608.20659v1 Announce Type: new Abstract: Methods that transfer predictions from two-dimensional foundation models into three-dimensional segmentation are commonly grouped by task or representat
arXiv:2608.20640v1 Announce Type: cross Abstract: Multi-merchant e-commerce catalogs contain equivalent and related products under different merchant-scoped identifiers, fragmenting behavioral evidenc
arXiv:2608.21224v1 Announce Type: new Abstract: Recently, there has been a great deal of research into improving AI methods and their application. The main focus is on tracking progress, enabling tran
arXiv:2608.20387v1 Announce Type: cross Abstract: While recent text-to-speech (TTS) models achieve high naturalness, controlling fine-grained expression via natural-language instructions remains chall
arXiv:2608.20757v1 Announce Type: cross Abstract: We describe the PSK submission to the WMT 2026 Multilingual Instruction Shared Task. Our system uses the 3.35B-parameter Tiny Aya Global model with th