arXiv:2605.11855v2 Announce Type: replace-cross Abstract: Sequence learning is dominated by Transformers and parallelizable recurrent neural networks (RNNs) such as state-space models, yet learning long-term dependencies remains challenging, and state-of-the-art designs trade power consumption for performance. The Bistable Memory Recurrent Unit (BMRU) was introduced to enable hardware-software co-design of ultra-low power RNNs: quantized states with hysteresis […]
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
arXiv:2605.16928v2 Announce Type: replace-cross Abstract: Long-context inference in large language models is bottlenecked by the quadratic cost of full attention. Existing efficient alternatives often rely either on native sparse training or on heuristic token eviction, creating an undesirable trade-off among efficiency, training cost, and accuracy. In this work, we show that full-attention LLMs are already […]
Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
arXiv:2606.01637v2 Announce Type: replace-cross Abstract: Large language models are increasingly used in multi-agent systems, where they see and respond to other agents’ answers. A key risk is conformity: a model may abandon its own answer simply because others agree on a different one. Prior studies show that LLMs often revise toward a majority answer, but […]
Scaling Decision-Focused Learning to Large Problems with Lagrangian Decomposition
arXiv:2606.08797v1 Announce Type: cross Abstract: Decision-focused learning has shown great promise for addressing predict-then-optimize problems, particularly in the presence of under-specified models. However, its practical deployment is often hindered by high computational costs and limited scalability, as it requires solving a constrained optimization problem for each training instance at every iteration. To address these challenges, […]
PAI: Preserving Amplitude Information in Representation-Based Time-Series Anomaly Detection
arXiv:2606.08935v1 Announce Type: cross Abstract: Representation-based time-series anomaly detection algorithms significantly outperform other methods on diverse anomaly detection tasks. However, we notice that they suffer from a major limitation in our evaluation – their learned embeddings are often amplitude-agnostic. Losing amplitude information can degrade performance on amplitude related anomalies, and this failure is prevalent across […]
See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video Understanding
arXiv:2606.09064v1 Announce Type: cross Abstract: Recent advances in Video Large Language Models (Video-LLMs) have enabled performance on long-video understanding tasks. However, existing methods still face two key limitations: evidence acquisition often relies on a single search intent, and answer generation lacks an effective visual feedback mechanism. To address these limitations, we propose textbfCoVER, a Comprehensive […]
Unified Energy for Invariant and Independent Decoding in Diffusion Language Models
arXiv:2606.09159v1 Announce Type: cross Abstract: Diffusion Language Models (DLMs) enable parallel text generation by iteratively denoising a full sequence, offering attractive flexibility compared to auto-regressive (AR) decoding. However, existing methods fail to fully capture token relationships, leading to a performance gap relative to AR baselines, especially as the degree of parallelism increases. In this paper, […]
Conan-embedding-v3: Fusing Modality-Specific Models for Omni-Modal Embedding
arXiv:2606.09331v1 Announce Type: cross Abstract: Omni-modal retrieval promises a single embedding space for text, image, video, document, and audio inputs, but building such a unified retriever is difficult since these modalities differ in data distribution, architecture, and optimization dynamics. In this work, we present Conan-embedding-v3, a decouple–fuse–recover framework for omni-modal retrieval. Conan-embedding-v3 first trains modality […]
Emergence of Context Characteristics Sensitivity in Large Language Models
arXiv:2606.09525v1 Announce Type: cross Abstract: During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query. While prior work has studied how context characteristics correlate with context usage by the LLM, this analysis has been limited to inference time, leaving open how these relationships are […]
ArtiFact: A Large-Scale Multi-Modal Cultural Heritage Dataset
arXiv:2606.09648v1 Announce Type: cross Abstract: Multi-modal data management has emerged as a central research topic in the database community, spanning data integration, semantic query processing, and data quality assessment. Despite this growing interest, the community lacks large-scale, real-world datasets combining tables, text, and images. We present ArtiFact, a multi-modal cultural heritage dataset of 651045 museum […]
Topological Neural Operators
arXiv:2606.09806v1 Announce Type: cross Abstract: We introduce Topological Neural Operators (TNOs), a principled framework for operator learning on cell complexes that lifts neural operators (NOs) from functions on points and/or edges to topological domains. TNOs represent data as features defined on cells of varying dimension and model their interactions through Discrete Exterior Calculus, enabling explicit […]
Automatic Extraction of Structured Information from Brain MRI Reports Using an Open-Weight Large Language Model
arXiv:2606.07721v1 Announce Type: new Abstract: Objectives: Automatic data extraction from free-text radiology reports enables large-scale research, but few studies assessed the performance of large language models (LLMs) on Dutch neuroradiology reports. Methods: We analyzed 947 brain MRI reports from a tertiary memory clinic (2016-2021), authored by consultant neuroradiologists. Trained medical students annotated thirty variables; 100 […]