Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2608.24053v1 Announce Type: new Abstract: Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space...
The paper introduces Giraffe, a new mapping architecture that converts hidden text token representations into visual embeddings for graphic design tasks. It uses a single [IMG] token per image and two shallow MLP blocks—one for training and one for inference—to compress and expand embeddings, trained with six loss functions. The approach achieves strong performance in both image‑to‑design and text‑to‑design generation while remaining lightweight.
CoMMa is a decentralized large language model (LLM) agent framework designed for oncology decision support. It allows specialists to work on partitioned clinical data streams, enforcing data decentralization and enhancing role specialization through agent-specific fine‑tuning. The framework introduces a contribution‑aware aggregation mechanism that replaces stochastic reasoning with deterministic embedding projections, enabling explicit credit assignment and a stable, interpretable decision pathway.
arXiv:2608.24782v1 Announce Type: new Abstract: Traditional image similarity metrics such as Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and the Structural Similarity Index Measure (...
arXiv:2608.24688v1 Announce Type: new Abstract: Precision oncology necessitates a longitudinal model of patient state that captures cancer evolution and treatment over time, integrating multimodal ob...
arXiv:2604.00313v3 Announce Type: replace Abstract: Underwater image classification is constrained by the cost of annotation and by the computational and methodological requirements of task-specific...
The paper introduces NAIMA, a guided depth super‑resolution framework that leverages global contextual semantic priors from pretrained vision transformer token embeddings. Its Guided Token Attention (GTA) module uses depth encodings as queries to attend over semantic tokens, with a zero‑initialized gate controlling the influence of semantic evidence. NAIMA achieves competitive in‑distribution performance while delivering superior cross‑dataset generalization without relying on decoded priors or auxiliary objectives.
MARS (Multi-Agent Relay of Specialized LLMs) is a prompt-only framework that assigns specialized LLM agents—each focused on a particular algorithmic domain such as dynamic programming, graphs, or geometry—to collaboratively solve competitive programming problems. Retrieval-augmented generation selects a small team of relevant specialists for each problem, and the agents iteratively refine a C++17 solution through sandboxed testing, passing structured packets between them until a final infrastructure-fixer normalizes the code. On the CodeContests benchmark, MARS achieves a pass rate of 0.624 with Gemma 4, improving over direct prompting by 14.4 percentage points while reducing wall‑clock cost and token‑spend variance compared to CodeSIM.
arXiv:2608.24665v1 Announce Type: new Abstract: Power outage prediction models are increasingly used in assessments of climate-driven infrastructure risk, yet current evaluation practices obscure whe...
The paper documents the migration of a live conversational recommendation system from a gradient‑boosted multiclass model to a pairwise‑binary deep recommender. It explains how reformulating the task, using negative sampling, noise injection, and attention pooling over transcript chunks enabled the new model to handle dynamic, multimodal data and long conversation context. The authors compare several architectures and loss functions, showing that the deep recommender matches or surpasses the CatBoost baseline, especially in later conversational stages.
arXiv:2608.23601v1 Announce Type: cross Abstract: EDA flow parameter tuning is critical for quality-of-results~(QoR), yet the parameter space is large, tightly coupled, and full evaluations are prohi...
arXiv:2604.19609v2 Announce Type: replace Abstract: Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong dom...
arXiv:2608.24592v1 Announce Type: cross Abstract: The embedding dimension of categorical predictors is usually selected through heuristic tuning, although it directly affects model complexity, approx...
The article examines how AI‑assisted item generation is filtered by a computational evaluator before expert review, focusing on representation, structural screening, and candidate‑form dependence. Through two in‑silico studies of 32,000 Big Five items, the authors show that subtle differences in semantic representation and structural evaluation lead to divergent item selections, even when overall content coverage appears stable. The findings reveal that the evaluator, often treated as a neutral technical step, actually shapes the evidence and wording that psychometricians ultimately review, highlighting its role as a revisable component of measurement design.
The paper presents a strictly causal streaming video anomaly detector that updates a fixed‑size state in constant time per frame, eliminating the need for clip buffering or lookahead. Its core is a diagonal linear state‑space recurrence with a decay gate, trained via self‑supervised next‑embedding prediction on a frozen visual backbone. The authors derive a closed‑form link between the recurrence’s decay spectrum and detection delay, validate on UCSD Ped2 and CUHK Avenue, and report real‑time latency on Apple M3 Pro hardware (≈0.75 ms per frame).
The study compares a custom capital gains calculation engine with a retrieval‑augmented generation (RAG) vector store of market advisory reports in a multi‑agent financial advisory system. A 2x2 factorial experiment showed that the tax‑optimization engine significantly reduced tax savings, while the RAG component had no significant effect. The RAG‑only condition yielded the highest tax savings, suggesting that pretrained language model knowledge may suffice for tax‑loss harvesting without specialized tooling.
PhysMLLMs introduces physics-inspired spatial continuity priors into video multimodal large language models to address spatio‑temporal inconsistencies such as jitter, drift, and identity switches. The method, called Global Representation Prior Alignment (REPA‑Global), distills global visual representations from a frozen DINOv2 teacher during training, aligning student representations without affecting inference speed. Experiments on multiple video benchmarks show improved segmentation mask quality and cross‑frame consistency, especially for challenging scenarios involving small targets, fast motion, occlusion, and distractors, while maintaining comparable performance on single‑frame image segmentation and general VLM tasks.
arXiv:2608.23571v1 Announce Type: new Abstract: Equivariant message-passing networks are the standard model for molecular property and interatomic-potential prediction, and recent work predicts the e...
The paper introduces Tlow, a flow-based item tokenizer that transforms raw semantic embeddings into a latent space following a standard normal distribution, enabling independent tokenization and simplifying distributional complexity. Tlow incorporates codebook guidance to align token embeddings with the codebook space, producing semantically clear token IDs. Experiments on four public datasets and an online multi‑modal retrieval task on WeChat show that Tlow improves recommendation performance and increases user click‑through rates by over 10%.
PHMForge is an evaluation environment that tests large language model agents on industrial prognostics tasks using the Model Context Protocol (MCP). It provides 99 SME-authored scenarios across eight asset classes, 39 MCP-native tools wrapping published PHM algorithms, and deterministic evaluators that separate protocol fluency, reasoning, instrumentation, and tool use. The benchmark shows that the best agent configuration achieves 80.8% pass@1, with orchestration and tool sequencing errors as the main failure modes, and demonstrates the limitations of static retrieval for prognostic computation.