Knowledge catalogue
arXiv:2609.08115v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) pretraining relies on an auxiliary load-balancing loss (LBL) to drive per-expert utilization toward uniformity. Post-training i
arXiv:2606.19376v2 Announce Type: replace Abstract: Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expe
arXiv:2609.05309v1 Announce Type: cross Abstract: Hyper-Connections and their manifold-constrained variant mHC widen a residual pathway from one stream to n, yet how trained models use this capacity r
arXiv:2609.02367v1 Announce Type: cross Abstract: Joint audio-video generation models have made substantial progress in visual quality and audio-visual synchronization. However, they still provide lim
arXiv:2609.01428v1 Announce Type: new Abstract: Large Language Model (LLM) agents based on the ReAct paradigm have demonstrated remarkable capabilities in tool use and task execution. However, ReAct s
arXiv:2608.30158v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is the de facto standard for adapting large language models (LLMs) to target domains, but it often degrades the model's g
arXiv:2608.30757v1 Announce Type: new Abstract: Before an intelligent system can decide whether an action is allowed, it must first know which rules the action has approached. A single proposed action
arXiv:2608.21454v1 Announce Type: new Abstract: The same fruit appears in a bunch, unpicked, peeled, bagged in plastic, or sliced on a dish, so automated fruit classification in the wild (AFCW) must a
arXiv:2608.21948v1 Announce Type: new Abstract: Complex clinical reasoning requires models to update diagnostic hypotheses as new evidence emerges and to coordinate different medical specialities unde
arXiv:2608.18410v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models process long multimodal token sequences, making inference expensive in both memory and computation. Existing efficie
arXiv:2608.17416v1 Announce Type: new Abstract: This paper addresses the multi-robot task allocation (MRTA) problem, which is essential for delivery and logistics applications. Our approach first defi
arXiv:2510.17088v3 Announce Type: replace-cross Abstract: Financial anomalies arise from heterogeneous mechanisms - price shocks, liquidity freezes, contagion cascades, and momentum reversals - yet ex
arXiv:2608.16721v1 Announce Type: new Abstract: The rapid evolution of text-to-image (T2I) generation models has effectively solved the foundational challenge of raw pixel synthesis, shifting the comm
arXiv:2608.15438v1 Announce Type: cross Abstract: Building approximate nearest neighbor (ANN) indexes at billion scale is often dominated by expensive global clustering or graph construction, making t
arXiv:2608.15951v1 Announce Type: new Abstract: We study when a wearable stress system should surface a prediction rather than change it. In low-stakes reflection and summary settings, aggregate accur
arXiv:2608.14682v1 Announce Type: new Abstract: Real-world time series inherently intertwine global periodic structures with localized non-stationary variations. Existing approaches process these hete
arXiv:2608.13571v1 Announce Type: cross Abstract: When a language model fails to answer a query on the first attempt, an agentic system retries, consuming additional tokens each time. This retry overh
arXiv:2608.10375v1 Announce Type: cross Abstract: Volatility control converts risk estimates into portfolio exposure, yet existing approaches often rely on a fixed volatility estimator or a pre-define
arXiv:2608.05219v1 Announce Type: new Abstract: Privileged on-policy distillation provides dense supervision for multi-turn agents by allowing a synchronized teacher to re-score the student's response
arXiv:2608.00322v1 Announce Type: cross Abstract: A robot that has to see and react on a fixed clock runs into two problems at once. Its cameras degrade in rain, mud, fog, and darkness. And the single
arXiv:2608.00576v1 Announce Type: cross Abstract: High-polyphony symbolic music is increasingly used in generation, analysis, and arrangement, yet many downstream tasks require bounded representations
arXiv:2607.27081v1 Announce Type: cross Abstract: Fine-tuning is the dominant paradigm for specializing large language models (LLMs), yet it exposes a critical vulnerability: malicious data providers
arXiv:2607.23676v1 Announce Type: new Abstract: LLM-based automated heuristic design (AHD) typically scores executable programs on complete instances or within fixed solver components. In large-scale
arXiv:2607.23734v1 Announce Type: cross Abstract: Unmanned aerial vehicles (UAVs) have emerged as a key enabler of next-generation Internet of Things (IoT) ecosystems, offering flexible aerial relayin
arXiv:2607.11987v1 Announce Type: new Abstract: Perineural invasion (PNI) is associated with poor postoperative outcomes in intrahepatic cholangiocarcinoma, but it is confirmed by surgical pathology.
arXiv:2607.06601v1 Announce Type: cross Abstract: Conditional computation can decouple language model quality from per-token inference cost, yet leading techniques act on a single axis in isolation: M
arXiv:2607.06481v1 Announce Type: cross Abstract: We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, vis
arXiv:2607.01670v1 Announce Type: new Abstract: Day-ahead wind power forecasting is essential for cost-effective power-system operation. It is primarily driven by future meteorological conditions whil
arXiv:2606.31201v1 Announce Type: new Abstract: Multi-objective masked image modeling (MIM) combines complementary learning signals (token distillation, CLS alignment, and pixel reconstruction) but ex
arXiv:2511.17979v2 Announce Type: replace Abstract: Diffusion models have achieved remarkable success in generative modeling, yet how to effectively adapt large pretrained models to new tasks remains
arXiv:2606.29335v1 Announce Type: cross Abstract: Multimodal speaker identification systems face two key challenges in real-world deployment: missing modalities and language mismatch between training
arXiv:2606.29541v1 Announce Type: new Abstract: Role-semantic assignments provide priors over how heterogeneous agents may coordinate, but cooperative MARL systems instead settle on conventions throug
arXiv:2509.04827v3 Announce Type: replace-cross Abstract: The energy cost of Large Language Model (LLM) inference is rapidly becoming a barrier to sustainable and scalable deployment. Although modern
arXiv:2606.21968v1 Announce Type: new Abstract: Vision-Language Models (VLMs) struggle as query-relevant objects become smaller. To address this, recent training-free approaches dynamically retrieve a
arXiv:2606.20621v1 Announce Type: cross Abstract: Multi-agent debate improves the reliability of large language models (LLMs) through iterative peer critiques. However, fixed topologies often introduc
arXiv:2606.20638v1 Announce Type: cross Abstract: Large language models are increasingly deployed as long-lived agents that must adapt across users, tasks, domains, modalities, and feedback regimes wi
arXiv:2606.21307v1 Announce Type: new Abstract: Continual learning (CL) is commonly studied under the assumption that sequential tasks are semantically related or structurally similar. However, in hig
arXiv:2506.14753v3 Announce Type: replace Abstract: Diffusion models are well known for their ability to generate a high-fidelity image for an input prompt through an iterative denoising process. Unfo
arXiv:2606.10338v1 Announce Type: cross Abstract: Machine unlearning is increasingly important for large language models, yet unlearning in Mixture-of-Experts (MoE) architectures remains underexplored
arXiv:2606.10617v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) merging can efficiently combine diverse generative capabilities from multiple trained LoRAs for a diffusion model. However, e
arXiv:2606.07710v1 Announce Type: cross Abstract: The autoregressive nature of large language models (LLMs) remains a significant bottleneck for inference, particularly in complex agentic workloads. W
arXiv:2602.00911v2 Announce Type: replace Abstract: The unit of collaboration in federated learning determines what guarantees are even expressible. Flat units like weights, prompts, raw examples, car
arXiv:2606.05859v1 Announce Type: new Abstract: Latent reasoning has emerged as a promising alternative to discrete Chain-of-Thought (CoT) in large language models (LLMs), enabling more expressive rea
arXiv:2606.04019v1 Announce Type: cross Abstract: Recent studies on sensor-language alignment have shown that two-stage frameworks can improve the semantic modeling ability of wearable-sensor human ac
arXiv:2606.01173v1 Announce Type: new Abstract: RGB-infrared detectors typically discard the statistics generated during cross-modal fusion, leaving downstream modules unaware of whether the current i
arXiv:2606.01106v1 Announce Type: new Abstract: TimeLogicQA evaluates whether video question answering systems can reason over temporal relations such as event existence, ordering, persistence, bounda
arXiv:2605.31229v1 Announce Type: cross Abstract: While retrieval is a core function of vision-language models, continually updating these models for retrieval tasks remains critically underexplored.
arXiv:2605.27336v1 Announce Type: new Abstract: Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sa
arXiv:2605.20708v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization,
arXiv:2605.20908v1 Announce Type: new Abstract: Concept-based (CB) models provide interpretability and support test-time human intervention, while standard neural networks (NN) offer strong task perfo
arXiv:2605.18853v1 Announce Type: cross Abstract: Edge deployment of Vision-Language Models (VLMs) faces a tradeoff between latency and accuracy: cloud execution provides high-quality predictions but
arXiv:2605.14241v1 Announce Type: new Abstract: Tool-augmented LLM agents increasingly access the same tool type through multiple functionally equivalent providers, such as web-search APIs, retrievers
arXiv:2510.05213v2 Announce Type: replace-cross Abstract: Pretrained vision foundation models (VFMs) advance robotic learning via rich visual representations, yet individual VFMs typically excel only
arXiv:2605.12965v1 Announce Type: new Abstract: Solutions to many partial differential equations (PDEs) display coexisting smooth global transport and localized sharp features within a single trajecto
arXiv:2605.09256v1 Announce Type: cross Abstract: We introduce a use of the (M)-cover (or (M)-layer) transform for machine learning. The method replicates a model (M) times, but instead of coupling th
arXiv:2605.08423v1 Announce Type: cross Abstract: We present a data-adaptive method for parameter-efficient fine-tuning of large neural networks. Standard low-rank adaptation methods improve efficienc
arXiv:2605.10805v1 Announce Type: new Abstract: Reasoning-capable large language models (LLMs) have recently been adopted as automated judges, but their benefits and costs in LLM-as-a-Judge settings r
arXiv:2605.08639v1 Announce Type: new Abstract: Load imbalance is a long-standing challenge in Mixture-of-Experts (MoE) training and is exacerbated in reinforcement learning (RL) for LLMs, where hot e
arXiv:2605.07111v1 Announce Type: cross Abstract: Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides the representational pla
arXiv:2605.07846v1 Announce Type: new Abstract: Coarse-mask local image editing asks a model to modify a user-indicated region while preserving the surrounding scene. In practice, however, rough masks