Knowledge catalogue
arXiv:2605.09839v1 Announce Type: cross Abstract: We introduce the Free Energy Manifold (FEM), a score-trained conditional energy model specialized for inference in hybrid Bayesian networks with discr
arXiv:2509.19771v5 Announce Type: replace-cross Abstract: Off-policy reinforcement learning suffers from extrapolation errors when a learned policy selects actions that are weakly supported in the rep
arXiv:2605.08712v1 Announce Type: new Abstract: Action-conditioned surgical video generation is a critical yet highly challenging problem for robotic surgery. The core difficulty is that low-dimension
arXiv:2605.09419v1 Announce Type: new Abstract: While experience replay is essential for data efficiency in reinforcement learning (RL), standard methods treat the replay buffer as a passive memory sy
arXiv:2510.13896v2 Announce Type: replace-cross Abstract: Cellular image segmentation is essential for quantitative biology yet remains difficult due to heterogeneous modalities, morphological variabi
arXiv:2605.10115v1 Announce Type: new Abstract: Tackling the task of materials generation, we aim to enhance the previously proposed All-atom Diffusion Transformer (ADiT) by introducing SymADiT, a sym
arXiv:2605.08733v1 Announce Type: new Abstract: Expressive generative policies such as diffusion and flow models are appealing for MaxEnt online reinforcement learning because of their ability to mode
arXiv:2605.10457v1 Announce Type: cross Abstract: Real-time Light Detection And Ranging (LiDAR) simulation must find, per emitted ray, the closest intersecting triangle even in dynamic scenes containi
arXiv:2605.08851v1 Announce Type: cross Abstract: The scarcity of high-quality imaging data for coronary angiography (CAG) stenosis limits the clinical translation of automated stenosis detection. Syn
arXiv:2509.20863v3 Announce Type: replace Abstract: Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approa
arXiv:2605.10108v1 Announce Type: new Abstract: Joint named entity recognition (NER) and relation extraction (RE) is a fundamental task in natural language processing for constructing knowledge graphs
arXiv:2605.09973v1 Announce Type: cross Abstract: Reliable detection of personally identifiable information (PII) is increasingly important across modern data-processing systems, yet the task remains
arXiv:2509.17815v2 Announce Type: replace Abstract: Global optimization, particularly for non-convex functions with multiple local minima, poses significant challenges for traditional gradient-based m
gpt-realtime-2 is a great voice model (with a typically bad OpenAI name). Voice models are natively processing speech, not transcribing it, so the intelligence of the model matters. The old voice mode
arXiv:2605.09408v1 Announce Type: new Abstract: Link prediction (inferring missing or future connections between nodes in a graph) is a fundamental problem in network science with widespread applicati
arXiv:2605.09100v1 Announce Type: new Abstract: Text embedding and generative tasks are usually trained separately based on large language models (LLMs) nowadays. This causes a large amount of trainin
arXiv:2605.10893v1 Announce Type: new Abstract: Large vision-language models suffer from visual ungroundedness: they can produce a fluent, confident, and even correct response driven entirely by langu
arXiv:2603.16253v2 Announce Type: replace-cross Abstract: Vision-language process reward models (VL-PRMs) are increasingly used to score intermediate reasoning steps and rerank candidates under test-t
arXiv:2605.10386v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly integrated into autonomous driving (AD) systems; however, they remain vulnerable to diverse sa
arXiv:2411.04077v2 Announce Type: replace Abstract: By leveraging both texts and images, large vision language models (LVLMs) have shown significant progress in various multi-modal tasks. Nevertheless
arXiv:2605.08292v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) models scale capacity by routing each token to a small subset of experts. However, their routers exhibit a fundamental
arXiv:2605.09465v1 Announce Type: new Abstract: High-precision heavy-duty grading is a common step in earthworks, traditionally carried out manually by skilled operators. Removing a significant amount
arXiv:2605.08665v1 Announce Type: new Abstract: Large reasoning models achieve high accuracy through extended chain-of-thought but generate 5--8 more tokens than necessary, applying verbose reasoning
arXiv:2602.09524v3 Announce Type: replace Abstract: Unsupervised industrial anomaly detection (UAD) is essential for modern manufacturing inspection, where defect samples are scarce and reliable detec
arXiv:2605.08143v1 Announce Type: cross Abstract: Large language models encode vast factual knowledge that inevitably becomes outdated or incorrect after deployment, yet retraining is costly prohibiti
arXiv:2605.10199v1 Announce Type: new Abstract: Full-duplex spoken dialogue requires a model to keep listening while generating its own spoken response. This is challenging for large language models (
arXiv:2605.09523v1 Announce Type: new Abstract: Neural operators provide fast surrogate models for time-dependent partial differential equations, but their standard autoregressive use usually assumes
arXiv:2605.08283v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a pivotal technique for enhancing the reasoning capabilities of Large Language Mo
arXiv:2602.06527v2 Announce Type: replace Abstract: Scaling test-time compute with multi-path chain-of-thought improves reasoning accuracy, but its effectiveness depends critically on the exploration-
arXiv:2605.10100v1 Announce Type: cross Abstract: We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperb
arXiv:2604.15113v2 Announce Type: replace Abstract: Vector Symbolic Architectures (VSAs) provide a well-defined algebraic framework for compositional representations in hyperdimensional spaces. We int
arXiv:2605.10009v1 Announce Type: new Abstract: Query-based image retrieval (QBIR) requires retrieving relevant images given diverse and often stylistically heterogeneous queries, such as sketches, ar
arXiv:2403.18136v3 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have gained popularity in numerous domains, yet they are vulnerable to backdoor attacks that can compromise their
arXiv:2602.22551v2 Announce Type: replace-cross Abstract: Cancer is often driven by specific combinations of an estimated two to nine gene mutations, known as multi-hit combinations. Identifying these
arXiv:2605.09127v1 Announce Type: new Abstract: Contact-implicit trajectory optimization (CITO) has attracted growing attention as a unified framework for planning and control in contact-rich robotic
arXiv:2601.21926v4 Announce Type: replace Abstract: Diffusion-based visuomotor policies built on 3D visual representations have achieved strong performance in learning complex robotic skills. However,
arXiv:2605.09870v1 Announce Type: cross Abstract: We propose SVAR-FM (Structural VAR with Flow Matching), a framework for time series causal discovery that treats a physics-based simulator as a mechan
arXiv:2601.03511v2 Announce Type: replace-cross Abstract: A major challenge for the operation of large language models (LLMs) is how to predict whether a specific LLM will produce sufficiently high-qu
arXiv:2605.09439v1 Announce Type: new Abstract: Generative models are powerful tools for sampling from a learned distribution P(Y mid X), and inverse-design methods invert this map to find an input x
arXiv:2412.18798v3 Announce Type: replace-cross Abstract: Transformer-based models have achieved remarkable success in multivariate time series forecasting (MTSF) by capturing long-range dependencies.
arXiv:2605.08686v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typ
arXiv:2603.02676v2 Announce Type: replace-cross Abstract: Large language models suffer from content effects in reasoning tasks, particularly in multi-lingual contexts. We introduce a novel method that
arXiv:2605.09132v1 Announce Type: new Abstract: Vision--language models (VLMs) show promise for clinical decision support in radiology because they enable joint reasoning over radiological images and
arXiv:2605.08635v1 Announce Type: new Abstract: Reconstructing dynamic 3D scenes from blurry monocular videos is challenging as motion-induced blur entangles object motion and geometry, hindering geom
arXiv:2605.09487v1 Announce Type: new Abstract: Modern embodied agents achieve impressive performance, but their task knowledge is often stored in neural weights, latent state, or prompt-bound memory,
arXiv:2601.11258v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) face the 'knowledge cutoff' challenge, where their frozen parametric memory prevents direct internalization of ne
arXiv:2605.08806v1 Announce Type: new Abstract: Existing 2D-3D lifting human pose estimation methods have achieved strong performance. But the utilization of historical pose representations across net
arXiv:2605.08156v1 Announce Type: cross Abstract: Zero-shot recognition aims to classify an image by selecting the most compatible label description from a set of candidate classes without any task-sp
arXiv:2605.08755v1 Announce Type: new Abstract: Large reasoning models (LRMs) reach competition-level math and coding accuracy via long autoregressive decoding, making per-token decoding cost a primar
arXiv:2605.08732v1 Announce Type: cross Abstract: Modern vision-based world models can represent observations as compact yet expressive latent manifolds, but fast goal-oriented planning in these space
arXiv:2605.08496v1 Announce Type: new Abstract: Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of ex
arXiv:2605.08605v1 Announce Type: cross Abstract: We introduce the Lattice Deduction Transformer (LDT), a recurrent transformer that approximates logically sound deduction by projecting its latent sta
arXiv:2605.08279v1 Announce Type: cross Abstract: Learning predictive world models from visual observations is a core problem in embodied AI, with applications to model-based reinforcement learning an
arXiv:2605.09053v1 Announce Type: new Abstract: Online topological planning has become an effective paradigm for Vision-Language Navigation in Continuous Environments (VLN-CE), but existing methods st
arXiv:2605.09806v1 Announce Type: cross Abstract: Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated
arXiv:2605.09295v1 Announce Type: new Abstract: Text-to-SQL translates natural language questions into executable SQL queries, enabling intuitive database access for non-experts. While large language
arXiv:2512.06571v3 Announce Type: replace Abstract: Learning fast and robust ball-kicking skills is a critical capability for humanoid soccer robots, yet it remains a challenging problem due to the ne
arXiv:2605.10855v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated remarkable progress in chart understanding, largely driven by supervised fine-tuning (SFT) on increasing
arXiv:2605.09665v1 Announce Type: cross Abstract: Data selection is a key component of efficient instruction tuning for large language models, as recent work has shown that data quality often matters
arXiv:2303.05307v2 Announce Type: replace-cross Abstract: We study general-sum, multi-player stochastic games with transferable utility, motivated by settings where agents can use side payments to mak