Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2610.02926v1 Announce Type: new Abstract: Standard factual benchmarks assume clean monolingual prompts and exact-match scoring, two assumptions that break simultaneously in real-world multiling...
arXiv:2610.03000v1 Announce Type: cross Abstract: Intrinsic explainability remains a challenging problem, particularly in contexts where multilayer perceptrons (MLPs) require dynamic re-training with...
arXiv:2610.02718v1 Announce Type: cross Abstract: Vision-language models such as CLIP exhibit strong semantic generalization, but remain limited in fine-grained visual perception. A recent work named...
arXiv:2610.02224v1 Announce Type: new Abstract: Rapid and reliable identification of pharmaceutical residues is important for safeguarding public health, ensuring food safety, and enabling practical...
arXiv:2604.10800v2 Announce Type: replace-cross Abstract: Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verif...
arXiv:2606.20627v2 Announce Type: replace Abstract: Joint-Embedding Predictive Architectures (JEPAs) enable agents to plan in latent space by imagining the outcomes of candidate actions, yet task spe...
arXiv:2610.02953v1 Announce Type: new Abstract: Long-context LLM serving is increasingly bottlenecked by KV-cache memory, especially in resource-constrained scenarios. Among existing KV-cache compres...
arXiv:2610.02798v1 Announce Type: new Abstract: The Muon optimizer applies spectral orthogonalization to matrix-valued updates and has shown strong performance in large-scale neural network training,...
The paper critiques current memorization audits for generative models, arguing that lacking a proper null distribution leads to misleading conclusions. It introduces two exact null tests—one permutation test for whole models and a calibrated test for single images—showing that many previously flagged memorizations disappear under these stricter controls. The authors also propose a scale‑restricted statistic based on the Intersection Euler Characteristic Profile to better detect distinct copied images.
HADRec is a Hierarchy-Aware Drug Recommendation framework that fuses molecular knowledge and electronic health records to improve medication recommendation. It uses LLaMA-7B to encode clinical notes, ChemBERTa to encode drug SMILES strings, and a cross‑attention mechanism for multimodal fusion, while a hierarchical predictor and consistency constraint loss enforce adherence to the ATC classification system. Experiments on MIMIC‑III and MIMIC‑IV show state‑of‑the‑art performance, strong generalization, and well‑calibrated predictions, with counterfactual evaluation indicating clinically aligned reasoning.
The paper introduces Commute-Time-Preserving World Models (CTWMs), which learn latent representations that reflect commute-times in an environment by using a latent displacement predictor and a log-determinant regularizer. This approach addresses the issue that existing self-supervised methods degrade the necessary eigenvalue-dependent scaling for accurate commute-time representation. In experiments, CTWMs outperform the task-agnostic baseline LeWM on several continuous goal-reaching benchmarks while using only half the parameters.
ibUMAP introduces a coherent, field‑based alternative to UMAP’s stochastic negative sampling, evaluating attraction and repulsion from a shared embedding snapshot synchronously. By representing the degree‑weighted repulsive field with three scalar moments and using an interpolation‑based FFT scheme, it avoids explicit all‑pairs computations while maintaining efficient CPU and GPU performance. Benchmarks show median speedups of 3.29× (CPU) and 1.44× (GPU) over existing implementations, with improved run‑to‑run stability and controlled fidelity trade‑offs.
MiLoop is a reinforcement‑learning‑based constructive framework for neural combinatorial optimization that propagates selective memory across rollout steps. By fusing current embeddings with historical memory before attention layers and applying adaptive gated updates afterward, it enables a shallow policy to learn dynamic embeddings without external solution labels or search‑space pruning. Experiments on four combinatorial optimization problems show MiLoop consistently generates high‑quality solutions for instances ranging from 100 to 10 million nodes, demonstrating strong generalization.
The paper introduces a method called Debias Anything that jointly addresses fairness and diversity in diffusion models without requiring sensitive-attribute annotations. By connecting a frozen diffusion model to a pretrained vision-language embedding space via an adapter, the approach uses pairs of text prompts to guide batch composition toward desired attribute proportions and employs a disagreement score to promote diversity. The method is applicable to both unconditional and text-conditional diffusion models and demonstrates improved quality and diversity while maintaining comparable fairness levels in experiments.
The paper presents a systematic comparison of recurrent neural networks and Transformer models for iterative diffusion MRI tractography, focusing on training strategies, input representations, and hyperparameter tuning. It introduces a generation‑validation phase that provides streamline‑level supervision, enabling the models to achieve the best performance reported on the ISMRM2015 challenge dataset. The study also evaluates the effects of missing bundles, noisy training data, and invalid fibers, and demonstrates applicability to in‑vivo data from the Tractoinferno database.
AnchorPrompt is an adaptation technique for large audio‑language models that keeps the base model frozen and learns a single block of prompt vectors inserted at the decoder input. By training these prompts through self‑distillation on diverse audio and text perturbations, the method improves answer consistency and reduces hallucinations across multiple benchmarks. The approach is perturbation‑agnostic at inference, enabling zero‑shot transfer to unseen distortions such as reverberation and choice permutations.
The paper introduces INTRA, an attention-based encoder-decoder framework that retrieves directly from its own internal representations instead of using an external retriever. By having decoder attention query pre-encoded evidence chunks, INTRA unifies retrieval and generation, eliminating the typical mismatch seen in retrieval-augmented generation pipelines. Experiments on question-answering benchmarks show that INTRA outperforms strong engineered retrieval pipelines in both evidence recall and overall answer quality.
The paper introduces ReMILP, a reformulation‑contrastive learning framework that uses self‑supervision from equivalent formulations of mixed‑integer linear programs (MILPs). By distinguishing re‑descriptions and substitutions, the method trains a graph neural network and a hypernetwork to predict how variable embeddings transform under changes of variables, achieving invariance and equivariance without solver‑derived labels. The learned representations prove useful for tasks such as binary solution, constraint activity, and integrality gap prediction, and serve as a strong initialization for fine‑tuning.
Latent JEPA is a new framework that trains continuous latent thoughts to anticipate informative aspects of future solutions in chemical reasoning, without verbalizing every intermediate step. It combines autoregressive learning with joint-embedding prediction of one or more future views, using textual and molecular prediction objectives that link latent thoughts to subsequent reasoning and molecular outcomes. Experiments on ChemCoTBench demonstrate improvements in molecular optimization, editing, and reaction metrics, and representation analyses show that future prediction makes latent thoughts more informative about molecular outcomes and better aligned with chemical structure.
The paper introduces the Tree-Structured Factor Composition Network (TFCN), a surrogate model that decomposes spacecraft thermal configurations into reusable local physical factors and learns their global temperature-field response via a tree-structured composition module. Trained on configurations with up to 15 heat-generating components, TFCN is evaluated on unseen setups with 16–25 components, achieving out-of-distribution RMSE reductions of 65.6% and 33.6% compared to the best baseline for prescribed-temperature and radiative-flux boundary conditions, respectively. These results demonstrate that TFCN can reliably predict temperature fields across varying component counts, enabling efficient rapid evaluation and large-scale screening in spacecraft thermal design.