arXiv:2510.10285v3 Announce Type: replace Abstract: Multimodal large reasoning models (MLRMs) often suffer from hallucinations that stem not only from insufficient visual grounding but also from imbalanced allocation between perception and reasoning processes. Building upon recent interpretability findings suggesting a staged division of attention across layers, we analyze how this functional misalignment leads to two complementary […]
Characterizing MARL for Energy Control: A Multi-KPI Benchmark on the CityLearn Environment
arXiv:2602.19223v2 Announce Type: replace Abstract: The optimization of urban energy systems is crucial for the advancement of sustainable and resilient smart cities, which are becoming increasingly complex with multiple decision-making units. To address scalability and coordination concerns, Multi-Agent Reinforcement Learning (MARL) is a promising solution. This paper addresses the imperative need for comprehensive and reliable […]
SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation
arXiv:2603.08329v1 Announce Type: cross Abstract: Answering complex, real-world queries often requires synthesizing facts scattered across vast document corpora. In these settings, standard retrieval-augmented generation (RAG) pipelines suffer from incomplete evidence coverage, while long-context large language models (LLMs) struggle to reason reliably over massive inputs. We introduce SPD-RAG, a hierarchical multi-agent framework for exhaustive cross-document question […]
A New Lower Bound for the Random Offerer Mechanism in Bilateral Trade using AI-Guided Evolutionary Search
arXiv:2603.08679v1 Announce Type: cross Abstract: The celebrated Myerson–Satterthwaite theorem shows that in bilateral trade, no mechanism can be simultaneously fully efficient, Bayesian incentive compatible (BIC), and budget balanced (BB). This naturally raises the question of how closely the gains from trade (GFT) achievable by a BIC and BB mechanism can approximate the first-best (fully efficient) […]
Enhancing low energy reconstruction and classification in KM3NeT/ORCA with transformers
arXiv:2511.18999v2 Announce Type: replace-cross Abstract: The current KM3NeT/ORCA neutrino telescope, still under construction, has not yet reached its full potential in neutrino reconstruction capability. When training any deep learning model, no explicit information about the physics or the detector is provided, thus they remain unknown to the model. This study leverages the strengths of transformers […]
FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
arXiv:2505.13109v5 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size grows proportionally with context length. While KV cache compression methods have been proposed to address this issue, KV […]
Cold-Start Active Correlation Clustering
arXiv:2509.25376v2 Announce Type: replace-cross Abstract: We study active correlation clustering where pairwise similarities are not provided upfront and must be queried in a cost-efficient manner through active learning. Specifically, we focus on the cold-start scenario, where no true initial pairwise similarities are available for active learning. To address this challenge, we propose a coverage-aware method […]
Exploring Deep Learning and Ultra-Widefield Imaging for Diabetic Retinopathy and Macular Edema
arXiv:2603.08235v1 Announce Type: cross Abstract: Diabetic retinopathy (DR) and diabetic macular edema (DME) are leading causes of preventable blindness among working-age adults. Traditional approaches in the literature focus on standard color fundus photography (CFP) for the detection of these conditions. Nevertheless, recent ultra-widefield imaging (UWF) offers a significantly wider field of view in comparison to […]
LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing
arXiv:2603.08453v1 Announce Type: cross Abstract: The quadratic complexity of the attention mechanism and the substantial memory footprint of the Key-Value (KV) cache present severe computational and memory challenges for Large Language Models (LLMs) processing long contexts. Existing retrieval-based methods often compromise semantic integrity through fixed-size chunking and suffer from inefficient linear scanning. In this paper, […]
Representing local protein environments with machine learning force fields
arXiv:2505.23354v5 Announce Type: replace Abstract: The local structure of a protein strongly impacts its function and interactions with other molecules. Therefore, a concise, informative representation of a local protein environment is essential for modeling and designing proteins and biomolecular interactions. However, these environments’ extensive structural and chemical variability makes them challenging to model, and such […]
BoxMind: Closed-loop AI strategy optimization for elite boxing validated in the 2024 Olympics
arXiv:2601.11492v2 Announce Type: replace Abstract: Competitive sports require sophisticated tactical analysis, yet combat disciplines like boxing remain underdeveloped in AI-driven analytics due to the complexity of action dynamics and the lack of structured tactical representations. To address this, we present BoxMind, a closed-loop AI expert system validated in elite boxing competition. By defining atomic punch […]
Jagarin: A Three-Layer Architecture for Hibernating Personal Duty Agents on Mobile
arXiv:2603.05069v2 Announce Type: replace Abstract: Personal AI agents face a fundamental deployment paradox on mobile: persistent background execution drains battery and violates platform sandboxing policies, yet purely reactive agents miss time-sensitive obligations until the user remembers to ask. We present Jagarin, a three-layer architecture that resolves this paradox through structured hibernation and demand-driven wake. The […]