arXiv:2606.13361v1 Announce Type: new Abstract: Right now, across the world, AI agents are repeating the same absurd act: to read one document, they each recompute it from scratch. Every agent re-runs prefill, the most compute-intensive step a large model takes, over identical text, only to rebuild a key-value (KV) cache identical to the one the […]
Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning
arXiv:2606.11767v2 Announce Type: replace-cross Abstract: Blind grasping with a dexterous hand is a crucial manipulation capability. Nevertheless, learning such tactile-only policies for real robots remains challenging due to the tactile sim-to-real gap and the limited expressiveness of sparse tactile signals. To bridge this gap, we propose a framework for tactile-only blind grasping that is deployable […]
TerraBench: Can Agents Reason Over Heterogeneous Earth-System Data?
arXiv:2606.13148v1 Announce Type: new Abstract: Climate and environmental decision-making increasingly requires reasoning across heterogeneous inputs, including gridded physical data, satellite imagery, geospatial context, and simulator outputs. Weather and climate foundation models can forecast well, but do not reason interactively in language, while large language models (LLMs) reason in language but cannot operate directly on high-dimensional […]
Scalable Deep Learning Framework for Global High-Resolution Land Use Reconstruction
arXiv:2606.11793v2 Announce Type: replace-cross Abstract: Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly driven by the uncertainties affecting the land surface representation and variability in Earth system models. To address this limitation, we present a data-driven framework AI4Land, for generating high-resolution historical reconstructions and future projections of key land […]
TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
arXiv:2606.13054v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization has emerged as a promising compression technique, offering significant reductions in model size and inference complexity. However, existing methods struggle with heavy-tailed activation distributions and therefore keep activations in high precision, […]
“Is This Not Enough?”: Asymmetries in Institutional Accountability and Collective Sensemaking in the Case of Canada’s Algorithmic Visa Triage System
arXiv:2606.13071v1 Announce Type: cross Abstract: This paper examines how algorithmic accountability in Canada’s visa system is articulated institutionally and experienced by applicants across borders. We analyzed Immigration, Refugees and Citizenship Canada (IRCC)’s Algorithmic Impact Assessment (AIA) for the temporary resident visa (TRV) triage system using the algorithmic decision-making adapted for the public sector (ADMAPS) framework […]
Frozen Multimodal Embeddings for AI-Assisted Interview Assessment of Personality and Cognitive Ability
arXiv:2606.11930v2 Announce Type: replace-cross Abstract: Predicting psychological traits from asynchronous video interviews (AVIs) is a challenging problem in AI-assisted interview assessment because labeled datasets are limited while each response contains high-dimensional visual, acoustic, and verbal signals. This paper presents our solution for the ACM Multimedia AVI Challenge 2026, which evaluates two tasks: Track~1 predicts self-reported […]
A quantum-like benchmark for context-sensitive associative memory with adaptive plasticity
arXiv:2606.12449v1 Announce Type: new Abstract: Learning and memory require a balance between plasticity and stability: synaptic connections must encode new information without collapsing, saturating, or erasing previously useful structure. Associative-memory models can appear to learn successfully when fixed background connectivity already carries part of the task, making it difficult to distinguish genuine recall dynamics from […]
Deep Sleep Classification via EEG Signal Criticality: A Passive BCI Approach for Sleep-Improvement Neurofeedback
arXiv:2606.13017v1 Announce Type: new Abstract: Automated sleep staging is a fundamental application of passive Brain-Computer Interfaces (pBCI), decoding spontaneous neural states to enable closed-loop interventions independent of user intent. This study evaluates criticality features derived from Detrended Fluctuation Analysis (DFA) for the specific identification of deep sleep (N3). We analyzed $347,232$ EEG epochs from $290$ […]
EA-WM: Event-Aware World Models with Task-Specification Grounding for Long-Horizon Manipulation
arXiv:2606.13053v1 Announce Type: cross Abstract: Pretrained-feature world models provide a useful substrate for robot imagination, but visual or latent prediction alone does not determine whether an imagined future satisfies task-relevant events. Long-horizon manipulation requires progress signals that are relational, predicate-level, and physically grounded: whether an object has moved, whether a drawer or contact state has […]
Irregular curvature at focal adhesions modulates Piezo1 activity and low frequency ultrasound induced apoptosis in cancer cells
arXiv:2606.13047v1 Announce Type: new Abstract: Low-frequency, low intensity ultrasound (LIUS) has emerged as a promising physical modality capable of inducing selective apoptosis of cancer cells, while sparing healthy epithelial cells and fibroblasts. Hitherto, the mechanism underlying this selectivity has been unclear, but we now propose and develop a theoretical framework linking the distinct mechanical behaviours […]
ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning
arXiv:2606.13197v1 Announce Type: new Abstract: Multi-agent debate (MAD) can improve large language model reasoning, but fixed debate pipelines often waste computation and can amplify correlated errors among similar agents. We propose ARMOR-MAD, a training-free heterogeneous MAD framework that treats debate as conditional computation. ARMOR-MAD combines three components: Pre-debate Agreement Routing (PAR) decides whether independently generated […]