Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2607. 01082v1 Announce Type: new Abstract: Spatio-temporal point-process models must often generalise across space when local event histories are sparse.
arXiv:2504. 15388v3 Announce Type: replace-cross Abstract: In the context of multivariate nonparametric regression with missing covariates, we propose Pattern Embedded Neural Networks (PENNs), which can be applied in conjunction with any existing imputation technique.
arXiv:2605. 00366v4 Announce Type: replace-cross Abstract: High-capacity associative memories based on Kernel Logistic Regression (KLR) exhibit strong storage capabilities, but the dynamical and geometric mechanisms underlying their stability remain poorly understood.
arXiv:2607. 00341v1 Announce Type: cross Abstract: Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT).
arXiv:2607. 00402v1 Announce Type: cross Abstract: Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts.
arXiv:2607. 00140v1 Announce Type: cross Abstract: As computing education expands beyond traditional programming into operational domains such as systems administration and command-line environments, existing pedagogical frameworks struggle to capture a dimension that is critical in these contexts: the real-world consequences of learner actions.
Large scale document deduplication must preserve semantic equivalence while remaining efficient over massive corpora. We present SemHash LLM, a multi granularity framework that unifies semantic projection hashing, attention weighted MinHash, contrastive boundary learning, and selective LLM based adjudication.
How Pandas chunking, Dask, and Polars help process millions of records when adding more compute isn't an option. The post What Can We Do When Memory Becomes the New Bottleneck in Data Engineering?
Congratulations to the Berkeley Artificial Intelligence Research (BAIR) Lab class of 2026! This year, BAIR celebrates another remarkable group of Ph.
While recent advancements like the Poincaré ResNet have demonstrated the potential of learning visual representations directly in hyperbolic space, their optimisation remains hampered by the computationally intensive nature of Riemannian gradients and the strict boundaries of the manifold. Furthermore, standard hyperbolic networks treat spatial transformations of the same object as distinct hierarchical concepts, leading to redundant parameter usage and vanishing signals.
arXiv:2606. 31156v1 Announce Type: cross Abstract: RAG systems retrieve documents optimized for answering one query at a time.
arXiv:2606. 31248v1 Announce Type: cross Abstract: Kilometer-scale convection shapes precipitation extremes, tropical organization, and cloud feedbacks, but most global atmospheric models approximate these processes at 25-100 km resolution.
arXiv:2606. 30902v1 Announce Type: cross Abstract: T cell receptor (TCR)-epitope binding prediction is essential for understanding adaptive immunity and developing immunotherapies.
arXiv:2601. 23088v2 Announce Type: replace-cross Abstract: Semantic caching has emerged as a pivotal technique for scaling LLM applications, widely adopted by major providers including AWS and Microsoft.
arXiv:2604. 19047v2 Announce Type: replace-cross Abstract: Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity.
arXiv:2606. 31119v1 Announce Type: new Abstract: Graphs are commonly visualized in 2D, where humans readily interpret spatial relationships, yet such layouts often distort higher-dimensional structure.
arXiv:2606. 32022v1 Announce Type: new Abstract: Residual-stream analysis asks how language-model computation evolves across depth, but intermediate decoding requires comparable readout coordinates across layers.
arXiv:2606. 30934v1 Announce Type: new Abstract: Modern text-to-image diffusion models, such as diffusion transformers (DiT), rely on timestep or prompt embeddings to modulate the strength of the denoising process in each timestep.
arXiv:2502. 15845v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often hallucinate, limiting their reliability in sensitive applications.
arXiv:2512. 04390v2 Announce Type: replace-cross Abstract: Joint video super-resolution and deblurring (VSRDB) requires both efficient long-range temporal modeling and robustness to frame-wise exposure-duration variation, which changes the extent of motion blur across video frames.