Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2608. 01586v1 Announce Type: cross Abstract: In recent years, numerous open-source software libraries have been developed for computing sets of features from univariate time series.
arXiv:2608. 01585v1 Announce Type: cross Abstract: Language model benchmarking is a difficult task.
arXiv:2608. 01875v1 Announce Type: cross Abstract: Most time series (TS) models are specialized for a single task, either understanding (i.
arXiv:2608. 02509v1 Announce Type: cross Abstract: Sequential decision-making in real-world applications often involves uncertainty about the environment's model.
arXiv:2602. 11133v2 Announce Type: replace Abstract: Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient because many tokens reach stability long before the final denoising step.
arXiv:2608. 02306v1 Announce Type: cross Abstract: We introduce a mathematical framework for shape comparison based on mapping functions from the shape domain to a common reference domain.
arXiv:2509. 06419v2 Announce Type: replace Abstract: Time-series anomaly detection is crucial in AIOps for maintaining large-scale service reliability.
arXiv:2608. 01142v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning, but standard LoRA produces a single deterministic model and does not directly support predictive uncertainty estimation.
arXiv:2510. 09379v2 Announce Type: replace Abstract: While softmax attention drives state-of-the-art performance in sequence modeling, its quadratic complexity motivates linear alternatives such as state space models (SSMs).
arXiv:2602. 10441v2 Announce Type: replace Abstract: Data lakes have become a fundamental platform for large-scale machine learning by enabling flexible management of heterogeneous data.
arXiv:2608. 01473v1 Announce Type: cross Abstract: Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leading to costly inference and limited spatial traceability for generated answers.
arXiv:2608. 02049v1 Announce Type: cross Abstract: Bosonic quantum systems provide a hardware-efficient platform for quantum information processing but remain challenging to characterise due to their large Hilbert space and the high measurement cost of state tomography.
Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much protection these safeguards provide, or how consistently across developers. We introduce the FAR.
Merchant risk control at large payment platforms screens tens of millions of merchants daily, where false positives harm legitimate merchants and false negatives leave harmful activity undetected. The hardest cases require jointly understanding a merchant's textual profile and long behavioral sequence.
Parameter-efficient post-training reduces the number of trainable parameters, but still requires repeated end-to-end backpropagation through the frozen backbone. Every adaptation step therefore needs backward-capable hardware and must store or recompute activations.
As generated videos become increasingly realistic, reliable video forgery detection is increasingly important. Existing studies typically optimize and use video forgery detectors as black boxes, while the latent forgery-discriminative knowledge inside them remains largely unexplored.
Prerequisite relation learning is central to adaptive instruction, yet existing methods often formulate it as conventional link prediction, limiting their ability to adaptively integrate complementary educational evidence for individual candidate pairs and to discourage contradictory reverse predictions. We propose ProPRL, a Property-aware Prerequisite Relation Learning framework.
The attention score with rotary position embeddings (RoPE) decomposes exactly into a sum over its 2D-rotation frequency pairs, and each pair's wavelength limits how far it can discriminate position. Aligned with this structure, we propose the per-RoPE-wavelength distance window: it prunes the query--key inner-product terms beyond a wavelength-proportional distance.
Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-of-the-art optimizers like GEPA (Genetic-Pareto) have argued that reflective instruction evolution can outperform traditional reinforcement learning and few-shot optimization.
Revenue forecasts guide acquisition budgets, demand planning, and customer-based valuations, yet an aggregate forecast does not show whether change reflects acquisition, repeat purchasing, spending per order, or offsetting movements. Using weekly transaction panels for 966 companies in 25 industries, the authors develop the Customer-Based Multi-task Transformer (CBMT), which learns shared structure, retains separate primitive forecasts, and aligns their combination with downstream revenue.