Knowledge catalogue
arXiv:2605.31189v1 Announce Type: new Abstract: Tabular prediction in high-stakes domains requires models that are accurate, transparent, and robust to imperfect inputs. We propose FlagGAM, a rule-def
arXiv:2601.22787v2 Announce Type: replace Abstract: Post-training compression is currently divided into two contrasting regimes. On the one hand, fast, data-free, and model-agnostic methods (e.g., NF4
arXiv:2601.01075v2 Announce Type: replace-cross Abstract: Embodied systems experience the world as 'a symphony of flows': a combination of many continuous streams of sensory input coupled to self-moti
arXiv:2605.30371v1 Announce Type: cross Abstract: We address the issue of global convergence in stochastic continuous optimization. For that purpose, we formulate the Canonical Evolutionary Strategy (
arXiv:2605.31042v1 Announce Type: cross Abstract: LLM agents are evolving from conversational chatbots to operational tools in real-world workspaces. In local agentic harnesses, an LLM can read and wr
arXiv:2603.18382v2 Announce Type: replace Abstract: Anonymization is often assumed to protect privacy once explicit identifiers are removed, because re-identification has historically required special
arXiv:2605.31400v1 Announce Type: new Abstract: Real-world image deblurring demands both high-fidelity restoration and computational efficiency, a balance existing methods often struggle to achieve. I
arXiv:2601.19936v2 Announce Type: replace-cross Abstract: The opacity of massive pretraining corpora in Large Language Models (LLMs) raises significant privacy and copyright concerns, making pretraini
arXiv:2605.30529v1 Announce Type: cross Abstract: Sentence-embedding models for semantic search are overwhelmingly developed and evaluated on English corpora. When applied to clinical retrieval in oth
arXiv:2605.31129v1 Announce Type: new Abstract: Multi-scale modeling has emerged as an effective design principle for time-series forecasting by capturing temporal dynamics at multiple resolutions. As
arXiv:2605.30568v1 Announce Type: new Abstract: LLM-as-a-Judge is a scalable alternative to human evaluation, yet existing rubric-based methods rely on human-annotated data such as reference answers o
arXiv:2605.30747v1 Announce Type: new Abstract: Logical rules constitute a cornerstone of knowledge graph (KG) reasoning, valued for their interpretability and ability to model relational patterns. Ho
arXiv:2601.19966v2 Announce Type: replace-cross Abstract: We introduce ELECTRAFI, a fast, end-to-end differentiable model for predicting periodic charge densities in crystalline materials. ELECTRAFI c
arXiv:2408.10441v3 Announce Type: replace Abstract: For many low-resource languages, the only available language models are large multilingual models trained on many languages simultaneously. Despite
arXiv:2603.13875v2 Announce Type: replace Abstract: Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-ca
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:2603.23398v2 Announce Type: replace-cross Abstract: Generative modeling of discrete data, such as graphs, underpins many scientific and industrial applications, including molecular discovery and
arXiv:2605.31105v1 Announce Type: new Abstract: Large language models (LLMs) with extended context lengths rely on the key-value (KV) cache to support attention over prior tokens. However, maintaining
arXiv:2511.18760v2 Announce Type: replace Abstract: Informal mathematics has been central to modern large language model (LLM) reasoning, offering flexibility and efficient construction of arguments.
arXiv:2605.31000v1 Announce Type: cross Abstract: Training Large Language Models (LLMs) on heterogeneous clusters presents significant challenges for collective communication, as hardware from multipl
arXiv:2602.16165v2 Announce Type: replace-cross Abstract: Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and del
arXiv:2603.11600v2 Announce Type: replace Abstract: Deep reinforcement learning for continuous control often suffers from high variance, low energy efficiency, and poor generalization under distributi
arXiv:2605.31476v1 Announce Type: new Abstract: End-to-end autonomous driving has emerged as a compelling paradigm for learning planning directly from sensor observations, while recent world-model-bas
arXiv:2605.30745v1 Announce Type: new Abstract: Large Vision-Language Models have achieved unprecedented success in zero-shot recognition by aligning visual features with broad semantic concepts. Howe
arXiv:2605.30478v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) trains language models using programmatically checkable signals such as unit-test outcomes, enab
arXiv:2605.30917v1 Announce Type: cross Abstract: As large-scale visual-document corpora such as arXiv papers and enterprise PDFs continue to grow, visual-document retrieval has gained increasing atte
arXiv:2503.14190v3 Announce Type: replace Abstract: A common goal in analyzing time series data is to understand how events cause observed variations. We study whether Large Language Models (LLMs) can
Application owners and platform engineers have long faced a difficult choice: spend excessively by over-provisioning to guarantee quick startups, or minimize costs but endure slow cold starts. We are
arXiv:2603.19862v2 Announce Type: replace Abstract: Vision-Language Models like CLIP are extensively used for inter-modal tasks which involve both visual and text modalities. However, when the individ
arXiv:2605.31096v1 Announce Type: new Abstract: While visually grounded Chain-of-Thought (CoT) has emerged as a promising paradigm to enhance fine-grained perception in multimodal large language model
just a small zoom out on the vibe shift: in Feb 2025 @soumithchintala was talking about his dream of personal, local, private agents, most people didn't believe him. it's June 2026 and @pewdiepie has
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:2605.30785v1 Announce Type: new Abstract: LLM agents increasingly face long-horizon tasks such as web search and deep research in real-world applications, where accumulated context can cause lon
arXiv:2605.31312v1 Announce Type: cross Abstract: Multimodal hallucination remains a persistent challenge for Vision-Language Models (VLMs). Standard textual Direct Preference Optimization (DPO) often
arXiv:2412.18134v4 Announce Type: replace Abstract: Randomized self-reductions (RSRs) express f(x) using f evaluated at random correlated points, enabling self-correcting programs, instance-hiding pro
arXiv:2605.30829v1 Announce Type: new Abstract: Lower extremity computed tomography (CT) contains clinically relevant information for body composition analysis, sarcopenia assessment, and musculoskele
arXiv:2605.30380v1 Announce Type: new Abstract: Deep convolutional and transformer-based detectors achieve strong performance for SAR ship detection but are often computationally prohibitive for real-
arXiv:2605.31598v1 Announce Type: new Abstract: Video vision-language models (VLMs) are increasingly used in long-horizon and streaming settings, yet most video encoders still rely on spatiotemporal s
arXiv:2605.31584v1 Announce Type: cross Abstract: Long-context reasoning remains a central challenge for large language models, which often fail to locate and integrate key information in extensive di
arXiv:2605.31603v1 Announce Type: cross Abstract: Connector-based video unified models have demonstrated strong capability in instruction-grounded video synthesis, but integrating a large high-fidelit
arXiv:2605.30514v1 Announce Type: cross Abstract: Machine unlearning evaluation is structurally skewed: Why-type questions, which probe causal and relational knowledge, comprise less than 0.06% of Cou
arXiv:2605.30857v1 Announce Type: new Abstract: Instruction fine-tuning is employed to enhance the instruction-following ability of large language models (LLMs). As the amount of instruction fine-tuni
arXiv:2603.02630v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved great success in many real-world applications, especially the one serving as the cognitive backbone
arXiv:2602.07905v2 Announce Type: replace Abstract: Large Language Models (LLMs) have shown strong potential in complex medical reasoning yet face diminishing gains under inference scaling laws. While
arXiv:2605.31268v1 Announce Type: new Abstract: We present Mellum 2, an open-weight 12B-parameter Mixture-of-Experts (MoE) language model with 2.5B active parameters per token. Mellum 2 is a general-p
arXiv:2605.31163v1 Announce Type: cross Abstract: We introduce the design-model framework: a way to derive efficient recurrent sequence maps from explicit assumptions about memory. A design model writ
arXiv:2605.31171v1 Announce Type: cross Abstract: Multilingual Information Retrieval (MLIR) reflects real-world search environments in which queries and relevant documents may appear in different lang
MiniMax M3 launched on June 1, 2026 as the first open-weights model to combine frontier coding, a 1-million-token context window, and native multimodality. The model achieves top-tier performance on c
arXiv:2605.31010v1 Announce Type: new Abstract: Retrieval-augmented generation is intensively studied to ground large language models on external evidence. However, retrieving from a unified knowledge
arXiv:2605.30727v1 Announce Type: new Abstract: Deep research agents increasingly combine private local documents with external tools like web retrieval, creating a privacy risk: an agent's external q
arXiv:2410.15475v2 Announce Type: replace Abstract: Multimodal learning aims to preserve as much task-related information as possible from different inputs. However, current fusion designs often disto
arXiv:2508.16687v2 Announce Type: replace Abstract: Traditional embeddings represent datapoints as vectors, which makes similarity easy to compute but limits how well they capture hierarchies and comp
arXiv:2601.21372v2 Announce Type: replace Abstract: We present NEMO, a system that translates Natural-language descriptions of decision problems into formal Executable Mathematical Optimization implem
arXiv:2603.05529v2 Announce Type: replace-cross Abstract: Data critical to real-world decision-making is increasingly found within organizations. Such data is heterogeneous, constantly evolving, and o
arXiv:2605.31116v1 Announce Type: new Abstract: Recent perception-free end-to-end (E2E) autonomous driving methods bypass explicit perception outputs by compressing dense image patch tokens into compa
arXiv:2512.00919v2 Announce Type: replace-cross Abstract: We address the problem of causal effect estimation in the presence of hidden confounders using nonparametric instrumental variable (IV) regres
arXiv:2605.30758v1 Announce Type: new Abstract: Pairwise preference data is widely used in language-model evaluation and alignment, often for model ranking, reward modeling, or preference optimization
arXiv:2602.07721v3 Announce Type: replace-cross Abstract: KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scal
arXiv:2605.30512v1 Announce Type: new Abstract: Generating physics diagrams from text requires strict adherence to physical laws. While current generative models produce visually plausible outputs, th
arXiv:2605.30542v1 Announce Type: new Abstract: World models for embodied AI must be physically viable: constructed to answer intervention queries by representing the physical structure governing acti