Knowledge catalogue
arXiv:2605.11005v1 Announce Type: new Abstract: Mixture-of-experts (MoE) architectures enable trillion-parameter LLMs with sparsely activated experts. Expert parallelism (EP) is a widely adopted MoE t
arXiv:2605.12379v1 Announce Type: new Abstract: Many reinforcement learning (RL) tasks have discrete action spaces, but most generative policy methods based on diffusion and flow matching are designed
arXiv:2605.12122v1 Announce Type: cross Abstract: Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among
arXiv:2509.09838v2 Announce Type: replace Abstract: While Soft Actor-Critic (SAC) is highly effective in continuous control, its discrete counterpart (DSAC) performs poorly on challenging discrete-act
arXiv:2605.11210v1 Announce Type: new Abstract: We present a framework for distributed Pose Graph Optimization (PGO) by formulating the problem as a second-order continuous-time dynamical system evolv
arXiv:2602.15006v2 Announce Type: replace-cross Abstract: Gaussian Processes (GPs) are a powerful tool for probabilistic modeling, but their performance is often constrained in complex, large-scale re
arXiv:2509.26469v3 Announce Type: replace Abstract: Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treat
Do AI models really learn physics, or just learn what physics looks like? Flatiron's @_helenqu, with @PolymathicAI & CDS researchers including @ylecun, finds that models predicting in latent space rec
arXiv:2605.12178v1 Announce Type: cross Abstract: World models enable agents to anticipate the effects of their actions by internalizing environment dynamics. In enterprise systems, however, these dyn
arXiv:2605.12055v1 Announce Type: new Abstract: Large Language Models (LLMs) achieve strong linguistic performance, yet their internal mechanisms for producing these predictions remain unclear. We inv
Do multi-agent systems make LLM reasoning better? Most AI devs assume that it should. But this new paper shows that this is often not the case. It ran 22,500 deterministic trajectories across GAIA, SW
arXiv:2512.03199v2 Announce Type: replace Abstract: Biometric facial recognition models often demonstrate significant decreases in accuracy when processing real-world images, often characterized by po
Don’t be part of a medium. Create a new one. Don’t join a festival. Invent your own. Don’t just become the camera of the next generation. Become its grammar. Don’t wait for a category. Become the reas
arXiv:2510.04265v4 Announce Type: replace-cross Abstract: Pass@k is widely used to report the reasoning performance of LLMs, but it often produces unstable and potentially misleading rankings, especia
arXiv:2605.11683v1 Announce Type: new Abstract: Vision Transformers (ViTs) incur significant computational overhead due to the quadratic complexity of self-attention relative to the token sequence len
arXiv:2601.22334v2 Announce Type: replace Abstract: Differentially private stochastic gradient descent (DP-SGD) is the gold standard for training machine learning models with formal differential priva
arXiv:2605.11750v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are often brittle in fine-grained manipulation, where minor action errors during the critical phases can rapidly e
arXiv:2505.18780v3 Announce Type: replace-cross Abstract: Achieving versatile humanoid locomotion with a single policy presents a critical scalability challenge. Prevailing methods often rely on disti
arXiv:2605.12183v1 Announce Type: new Abstract: Drifting Models have emerged as a new paradigm for one-step generative modeling, achieving strong image quality without iterative inference. The premise
arXiv:2605.11467v1 Announce Type: new Abstract: Reasoning models post-hoc rationalize answers they have already committed to internally, producing chains of *reasoning theater*: deliberative-looking s
arXiv:2506.17501v3 Announce Type: replace-cross Abstract: Following successful large-vessel recanalization via endovascular thrombectomy (EVT) for acute ischemic stroke (AIS), some patients experience
arXiv:2605.11569v1 Announce Type: cross Abstract: Accurate short-term demand forecasting is crucial to airline revenue management, yet most existing systems fail to meet this need because current mode
arXiv:2605.11567v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models predominantly adopt action chunking, i.e., predicting and committing to a short horizon of consecutive low-level act
arXiv:2605.11369v1 Announce Type: new Abstract: Generating physically plausible dynamic motions of human-object interaction (HOI) remains challenging, mainly due to existing HOI datasets limited to st
Each environment now has its own version history with rollback. An audit log captures every change. Egress and secrets can be scoped per environment. Secrets in one environment aren't accessible from
arXiv:2605.10993v1 Announce Type: new Abstract: Memory capacity is a critical factor determining the performance of Vision-Language-Action (VLA) models in long-horizon manipulation tasks. Existing mem
arXiv:2605.12140v1 Announce Type: new Abstract: Myocardial point tracking (MPT) has recently emerged as a promising direction for motion estimation in echocardiography, driven by advances in general-p
arXiv:2605.12196v1 Announce Type: new Abstract: Accurate ultra-short-term wind power forecasting is critical for grid dispatch and reserve management, yet remains challenging due to the non-stationary
arXiv:2605.12002v1 Announce Type: new Abstract: Text-guided inpainting has made image forgery increasingly realistic, challenging both SID and IFL. However, existing methods often struggle to point ou
arXiv:2605.11480v1 Announce Type: new Abstract: Reward fine-tuning has become a common approach for aligning pretrained diffusion and flow models with human preferences in text-to-image generation. Am
arXiv:2506.13163v3 Announce Type: replace Abstract: We study the Logistic Contextual Slate Bandit problem, where, at each round, an agent selects a slate of N items from an exponentially large set (of
arXiv:2605.12019v1 Announce Type: new Abstract: Human Activity Recognition (HAR) is a core task in pervasive computing systems, where models must operate under strict computational constraints while r
arXiv:2605.11526v1 Announce Type: cross Abstract: Training a deep neural network with the outputs of selected layers satisfying linear constraints is required in many contemporary data-driven applicat
arXiv:2510.09333v2 Announce Type: replace-cross Abstract: Evaluating generative models is challenging because standard metrics often fail to reflect human preferences. Human evaluations are more relia
arXiv:2605.11582v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable potential in advertising scenarios such as ad creative generation and targeted advertising. However,
arXiv:2605.11019v1 Announce Type: new Abstract: Although large language models rely on chain-of-thought for complex reasoning, the overthinking phenomenon severely degrades inference efficiency. Exist
arXiv:2602.09725v3 Announce Type: replace-cross Abstract: Remote KV cache reuse fetches KV cache for identical contexts from remote storage, avoiding recomputation, accelerating LLM inference. While i
arXiv:2605.12297v1 Announce Type: new Abstract: Egocentric 3D hand pose estimation and gesture recognition are essential for immersive augmented/virtual reality, human-computer interaction, and roboti
arXiv:2605.12498v1 Announce Type: new Abstract: Reconstructing the absolute 3D pose and shape of the hands from the user's viewpoint using a single head-mounted camera is crucial for practical egocent
arXiv:2605.12335v1 Announce Type: cross Abstract: Electronic Health Records (EHR) contain rich longitudinal patient information and are widely used in predictive modeling applications. However, effect
arXiv:2605.12491v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve strong data-driven scaling by leveraging all-to-all self-attention. However, this flexibility incurs a computational
arXiv:2605.12079v1 Announce Type: new Abstract: Human-in-the-loop Bayesian optimization (HITL BO) methods utilize human expertise to improve the sample-efficiency of BO. Most HITL BO methods assume th
arXiv:2605.11695v1 Announce Type: new Abstract: Symbols are shared, but perception is private. We study emergent communication between heterogeneous visual agents through decentralized learning, askin
arXiv:2605.12453v1 Announce Type: cross Abstract: To address the issues of high interruption time and measurement report overhead under user equipment (UE) mobility especially in high speed 5G use cas
arXiv:2602.22347v2 Announce Type: replace Abstract: Foundation models for computational pathology are expected to facilitate the development of high-performing, generalisable deep learning systems. Ho
arXiv:2605.11093v1 Announce Type: new Abstract: Today's inference-time workloads increasingly depend on timely access to a model's internal states. We present DMI-Lib, a high-speed deep model inspecto
arXiv:2605.11463v1 Announce Type: new Abstract: Learning and representing the subjectivities of agents has become a challenging but crucial problem in the trajectory prediction task. Such subjectiviti
arXiv:2603.24577v2 Announce Type: replace Abstract: Accurate 3D reconstruction of deformable soft tissues is essential for surgical robotic perception. However, low-texture surfaces, specular highligh
arXiv:2605.11214v1 Announce Type: new Abstract: Hard constraints in generative sampling are typically enforced by projection, applied either once at the end of sampling or after every update. This bin
arXiv:2605.12198v1 Announce Type: new Abstract: Pedestrian motion, due to its causal nature, is strongly influenced by domain gaps arising from discrepancies between training and testing data distribu
arXiv:2605.11632v1 Announce Type: new Abstract: Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their o
arXiv:2605.11964v1 Announce Type: new Abstract: A target-guided proactive dialogue system aims to steer conversations proactively toward pre-defined targets, such as designated keywords or specific to
arXiv:2109.10616v2 Announce Type: replace Abstract: Recently, Transformer-based models have been proven effective in the abstractive summarization task by creating fluent and informative summaries. Ne
arXiv:2605.11775v1 Announce Type: cross Abstract: Policy entropy has emerged as a fundamental measure for understanding and controlling exploration in reinforcement learning with verifiable rewards (R
arXiv:2605.12435v1 Announce Type: new Abstract: Predicting rare extreme events such as wildfires from meteorological data requires models that remain reliable under evolving environmental conditions.
arXiv:2605.11722v1 Announce Type: new Abstract: Recent text-to-image (T2I) generators can synthesize realistic images, but still struggle with compositional prompts involving multiple objects, counts,
arXiv:2605.11598v1 Announce Type: new Abstract: The increasing adoption of data-driven decision-making in public health has established epidemic forecasting as a critical area of research. Recent adva
arXiv:2605.11328v1 Announce Type: new Abstract: Automated scientific discovery using large language models relies on identifying genuinely novel solutions. Standard reinforcement learning penalizes hi
arXiv:2605.11524v1 Announce Type: new Abstract: Data-driven identification of partial differential equations (PDEs) relies on sparse regression over a candidate library of differential operators, wher
arXiv:2605.11316v1 Announce Type: new Abstract: The Gauss-Newton matrix is widely viewed as a positive semidefinite approximation of the Hessian, yet mounting empirical evidence shows that Gauss-Newto