arXiv:2604.17725v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong promise for mining Electronic Health Records (EHRs) by reasoning over longitudinal clinical information to capture context-rich patient trajectories. However, leveraging LLMs for structured EHRs (e.g., standardized diagnosis and medication codes) presents two key challenges. First, translating time-stamped EHR sequences into plain text can […]
Voronoi-guided Bilateral 2D Gaussian Splatting for Arbitrary-Scale Hyperspectral Image Super-Resolution
arXiv:2604.17727v1 Announce Type: cross Abstract: Most existing hyperspectral image super-resolution methods require modifications for different scales, limiting their flexibility in arbitrary-scale reconstruction. 2D Gaussian splatting provides a continuous representation that is compatible with arbitrary-scale super-resolution. Existing methods often rely on rasterization strategies, which may limit flexible spatial modeling. Extending them to hyperspectral image super-resolution remains […]
DSAINet: An Efficient Dual-Scale Attentive Interaction Network for General EEG Decoding
arXiv:2604.18095v1 Announce Type: new Abstract: In real-world applications of noninvasive electroencephalography (EEG), specialized decoders often show limited generalizability across diverse tasks under subject-independent settings. One central challenge is that task-relevant EEG signals often follow different temporal organization patterns across tasks, while many existing methods rely on task-tailored architectural designs that introduce task-specific temporal inductive biases. […]
ToFiE, a Topology-aware Fiber Extraction workflow for 3D reconstruction of dense and heterogeneous biological fiber networks from microscopy images
arXiv:2604.18230v1 Announce Type: new Abstract: Fibrous networks are ubiquitous structural components in biology, spanning cellulose in plant cell walls, fibrin in blood clots, and collagen in the extracellular matrix of animal tissues. Theoretical models predict that network connectivity critically influences their mechanical behavior. However, accurately reconstructing network topology from 3D image data remains a major […]
WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation
arXiv:2604.18478v1 Announce Type: new Abstract: Persistent memory is the bottleneck separating stateless chatbots from long-running agentic systems. Retrieval-augmented generation (RAG) over flat vector stores fragments facts into chunks, loses cross-session identity, and has no first-class notion of supersession or contradiction. Recent bitemporal knowledge-graph systems (Graphiti, Memento, Hydra DB) add typed edges and valid-time metadata, but […]
How Robustly do LLMs Understand Execution Semantics?
arXiv:2604.16320v1 Announce Type: cross Abstract: LLMs demonstrate remarkable reasoning capabilities, yet whether they utilize internal world models or rely on sophisticated pattern matching remains open. We study LLMs through the lens of robustness of their code understanding using a standard program-output prediction task. Our results reveal a stark divergence in model behavior: while open-source reasoning […]
Training for Compositional Sensitivity Reduces Dense Retrieval Generalization
arXiv:2604.16351v1 Announce Type: cross Abstract: Dense retrieval compresses texts into single embeddings ranked by cosine similarity. While efficient for recall, this interface is brittle for identity-level matching: minimal compositional edits (negation, role swaps) flip meaning yet retain high similarity. Motivated by geometric results for unit-sphere cosine spaces (Kang et al., 2025), we test this retrieval-composition […]
Stream2LLM: Overlap Context Streaming and Prefill for Reduced TTFT
arXiv:2604.16395v1 Announce Type: cross Abstract: Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality). Recent work mitigates this via streaming–overlapping retrieval with inference–but prior systems focus on single-request settings and overlook challenges in multi-tenant […]
(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models
arXiv:2604.16429v1 Announce Type: cross Abstract: We introduce Mosaic, a probabilistic weather forecasting model that addresses two principal sources of spectral degradation in ML-based weather prediction: (1) deterministic training against ensemble means and (2) compressive encoding creating an information bottleneck. Mosaic generates ensemble members through learned functional perturbations and operates on native-resolution grids via block-sparse attention, […]
ContraPrompt: Contrastive Prompt Optimization via Dyadic Reasoning Trace Analysis
arXiv:2604.17937v1 Announce Type: new Abstract: Prompt optimization methods either analyze individual failures in isolation or compare prompt variants across examples, operating on single execution traces with no access to the reasoning process distinguishing success from failure on the same input. We introduce ContraPrompt, built on the observation that when a model fails but succeeds on […]
Boltzmann Machine Learning with a Parallel, Persistent Markov chain Monte Carlo method for Estimating Evolutionary Fields and Couplings from a Protein Multiple Sequence Alignment
arXiv:2604.18022v1 Announce Type: new Abstract: The inverse Potts problem for estimating evolutionary single-site fields and pairwise couplings in homologous protein sequences from their single-site and pairwise amino acid frequencies observed in their multiple sequence alignment would be still one of useful methods in the studies of protein structure and evolution. Since the reproducibility of fields […]
State Transfer Reveals Reuse in Controlled Routing
arXiv:2604.18158v1 Announce Type: new Abstract: Prompt-based interventions can change model behavior, but trained success alone does not identify where the behaviorally relevant state is represented. We study this question in controlled routing tasks using interfaces chosen on support data, held-out query evaluation, and matched necessity, sufficiency, and wrong-interface controls. On GPT-2 triop, an early interface […]