Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2608. 16837v1 Announce Type: cross Abstract: Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation.
arXiv:2608. 15690v1 Announce Type: cross Abstract: Text-to-audio-video (T2AV) generation models produce a video and its soundtrack from a textual description, but offer no control over whose voice speaks in the output.
arXiv:2405. 17678v2 Announce Type: replace-cross Abstract: Achieving zero-shot adversarial robustness without sacrificing generalization remains challenging for foundation models such as CLIP, especially under large adversarial perturbations.
arXiv:2508. 09105v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and contextual understanding of Large Language Models (LLMs) by introducing external knowledge sources.
arXiv:2608. 16198v1 Announce Type: cross Abstract: Dermatology models face distribution shifts in teledermatology settings, where submitted images differ from the training data in lighting, angle, distance, focus, and framing.
arXiv:2608. 14792v1 Announce Type: cross Abstract: Objectives: To determine whether zero-shot prompting of a large language model (LLM) is sufficient to detect shared decision-making (SDM) behaviors in real clinical encounters, and whether supervised learning adds value under patient-grouped, nested evaluation.
arXiv:2608. 16087v1 Announce Type: cross Abstract: Removing wearables from physiological monitoring also removes their supervision: the signal indicating where and when a stress response occurred.
arXiv:2608. 15001v1 Announce Type: cross Abstract: We construct spinning conformal fields from neural networks and the embedding formalism, computing their two-, three- and four-point functions in examples, building on scalar conformal field techniques introduced in \cite{Halverson:2024axc}.
arXiv:2602. 21819v3 Announce Type: replace-cross Abstract: Reconstructing dynamic visual experiences from brain activity provides a compelling avenue for exploring the neural mechanisms of human visual perception.
arXiv:2608. 14658v1 Announce Type: cross Abstract: We introduce pico-type, a byte-level multi-head content classifier with approximately 1.
arXiv:2608. 15574v1 Announce Type: cross Abstract: Video question answering systems built on vision-language models often produce timestamped claims with high confidence even when unsupported by the cited frame.
arXiv:2608. 15919v1 Announce Type: cross Abstract: Retrieval-Augmented Generation over knowledge graphs (Graph-RAG) has emerged as a powerful paradigm for grounding large language models in domain-specific corpora.
arXiv:2608. 15601v1 Announce Type: new Abstract: Compositional Concept Generalization (CoCoGen), the ability to systematically recombine learned primitives in novel contexts, is a key challenge for multimodal learning.
Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it challenging for conventional single-stage VLA architectures to coordinate locomotion, waist posture, and dual-arm manipulation effectively.
Retrieval-augmented and agentic question-answering systems increasingly re-derive the meaning of a corpus at query time. Put plainly, instead of re-deriving what a corpus means on every question, the work is done once when a document arrives and is thereafter merely consulted -- a compiler, not an interpreter, of meaning.
Enterprise Document Intelligence [Vol. 1 #13bis] - The four bricks return useful results most of the time.
Positional encoding is a fundamental component of Transformer-based generative recommendation models, where user histories are modeled as autoregressive item sequences. Most positional encoding methods are inherited from natural language processing and mainly represent discrete item order.
LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages, or tables) is query-dependent. Existing retrieval-augmented approaches pre-materialize evidence via fixed chunking, embeddings, or persistent indexes: effective for lookup, yet costly, stale-prone, and committed to a granularity before the query is known.
Removing wearables from physiological monitoring also removes their supervision: the signal indicating where and when a stress response occurred. Contactless stress sensing therefore becomes a weakly supervised evidence-localization problem, where a clip-level label must be traced to the body regions and moments that produced it.
arXiv:2608. 13939v1 Announce Type: cross Abstract: Ultrasound is the primary imaging modality for assessing thyroid nodules, and the ACR TI-RADS framework standardizes diagnosis through five ultrasound feature categories that are aggregated into five risk levels (TR1-TR5).