Geometry Matters in Packed 3D Attention
Packing a 3D volume into a token sequence is not merely long-sequence modeling. Once the volume is packed, sequence order no longer encodes the geometry of the sample---so a positional mechanism…
nlp
MLINFO COLLECTION
文書検索・社内QA
RAG、埋め込み、検索評価、要約を使って文書検索や社内QAを作るための技術です。
記事一覧
16 / 25Quantum-Inspired Pairwise Ranking Aggregation via Active LLM Feedback
Ranking aggregation from multiple retrievers is a powerful yet under-explored technique in modern retrieval and RAG systems. We introduce LLM-IRA, the first extension of the quantum-inspired…
nlp
SpectralTF-MAE: A Pre-trained Spectral Foundation Model for Tokamak Fusion Plasma Diagnostics
Spectroscopic diagnostics provide rich information for characterizing plasma states in tokamak fusion experiments, while existing learning-based approaches are often designed for individual tasks and…
deep-learning
SaiVLA-JEPA: Evaluating Future Latent Prediction in JEPA-Conditioned VLA Control
Joint-embedding predictive architectures (JEPAs) learn to predict representations rather than pixels, offering a compact way to model how visual scenes evolve. We ask whether this predictive…
deep-learning
Calibrating Track-Query Updates at Test Time for Multi-Object Tracking
Multi-Object Tracking (MOT) requires localizing multiple objects and maintaining their identities over time. Recent query-propagation trackers carry target-specific representations across frames and…
nlp
Geometry-Aware Trajectory State Modeling for Few-Shot Action Recognition
Few-shot action recognition (FSAR) requires representations that expose discriminative motion dynamics from only a few labeled videos. Recent trajectory-based methods leverage long-term point tracks…
nlp
Automatic Iconographic Annotation of Medieval Illuminations: Comparing Generative Vision-Language Models and Supervised Discriminative Classifiers
The large-scale digitisation of medieval manuscripts creates a growing need for automated iconographic indexing. We evaluate two complementary paradigms for this task on 9,735 full-folio images…
nlp
CoSTA: Co-Evolving Self-Play Timeline Agents for Complex Temporal Knowledge Graph Question Answering
Complex Temporal Knowledge Graph Question Answering (TKGQA) involves more than retrieving facts: the timestamp or validity interval of one fact can constrain the search for another, while multiple…
deep-learning
Structure-retained low-rank adapters for weather synthesis
Real-world deployment of computer vision models, particularly in outdoor scenarios, is often limited by environmental interferences, such as adverse weather. Improving model robustness across weather…
nlp
Visually Irrelevant Hallucinations in Medical Vision-Language Models
Medical vision-language models (VLMs) show strong performance in radiology report generation (RRG) and medical visual question answering (Med-VQA), producing free-form clinical descriptions and…
computer-vision
ELEVATE: Agentic Controller Acquisition from Task Failure for Quadrupedal Manipulation
Quadrupedal manipulators can extend their workspace through whole-body interaction, but task-planning agents' capabilities remain limited by their available controllers. We present ELEVATE, a…
nlp
TCC-RAG: Temporal Causal Chain-Guided RAG for Temporal Knowledge Graph Question Answering
Recent advances in large language models (LLMs) have spurred growing interest in temporal knowledge graph question answering (TKGQA). Most existing methods rely on semantic retrieval augmented…
nlp
Manifest-Assisted Retrieval in Artificial Intelligence Search: Evidence Gaps and a Security Evaluation
The external sources retained in our non-systematic audit did not isolate the incremental security or utility effect of consuming /llms.txt while ordinary retrieval remained fixed. The initial audit…
nlp
Knowledge-structured and evidence-aware semantic self-distillation for glomerular pathology foundation model
Visual foundation models learn rich pathological morphology but lack explicit concept-level supervision. Vision--language pretraining can provide this supervision but requires costly image--text…
deep-learning
Statutory Article Retrieval from Arabic Judicial Narratives: Family Law and Law of Evidence in Saudi Arabia
Reliable legal information retrieval must ground legal reasoning in authoritative statutory sources. In Arabic judicial settings, long factual narratives must be mapped to concise articles that…
nlp
What Should a Navigator Remember? Spatiotemporal Memory for Zero-Shot Vision-Language Navigation
Zero-shot vision-and-language navigation (VLN) requires an agent to use past observations without navigation-specific training. We study what information an 8B-scale navigation system should retain…
nlp
Hidden Commitment: When Language Models Silently Pick a Side and How Steering Can Surface It
Language-model answers are often treated as a visible record of the internal decision that produced them. We test this assumption in conflicting-context question answering, where two supplied…
nlp
Cross Lingual Abstractive Summarization for Marathi
Text summarization is an important task for advancing natural language processing (NLP) research and applications in Indic languages. Despite progress in extractive and abstractive summarization,…
deep-learning
Keepace.ai: A Technical Report on a Large Language Model for Sports and Health
Large language models hold promise for delivering safe, scientifically grounded, and personalized exercise guidance at scale, yet the sports-and-health domain still lacks curated training corpora and…
nlp
3DCodeEdit: Benchmarking Instruction-Guided 3D Program Editing
Language models increasingly create 3D content through code, with practical workflows often relying on editing existing programs rather than regenerating them, for speed and precise control. Such…
nlp
Two Birds with One Stone: Skill-Augmented Generation via Unified Retrieval and Utilization
Skills, as reusable external knowledge, have demonstrated substantial potential to enhance the ability of Large Language Models (LLMs) to solve complex tasks. However, existing skill-augmented…
nlp
Same Label, Different Interface: Beyond Action-Space Labels in Robot Learning
Robot-learning studies often compare position and velocity actions as though each label identified a single experimental treatment, yet the label alone does not determine what the robot executes.…
nlp
Small-scale neural simulation of Caenorhabditis elegans on Loihi-2 using NeuroML2Loihi
Neural simulation is an essential methodology for studying biological nervous systems, but it remains limited by the computational costs of repeatedly updating neural and synaptic states over many…
nlp
DR-Learners for Generalizing CATEs from a Randomized Controlled Trial
Randomized clinical trials are essential for evaluating interventions, yet average treatment effects can obscure treatment effect heterogeneity, making conditional average treatment effects (CATEs) a…
nlp