Empirical forensic study of OpenClaw recovers interaction traces, proposes an agent artifact taxonomy, and flags nondeterminism from LLM-mediated execution as a foundational issue for digital forensics.
Canonical reference
Deep spoken keyword spotting: An overview.IEEE Access, 10:4169–4199, 2022
Canonical reference. 78% of citing Pith papers cite this work as background.
62
Pith papers citing it
Background
78% of classified citations
citation-role summary
background 14
method 3
baseline 1
citation-polarity summary
representative citing papers
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
KV-cache sharing boosts multi-agent QA performance but enables undetectable tampering; HMAC manifests binding agent, session, and payload reliably detect changes.
A reinforcement learning agent for timing GenAI access improved post-test performance and metacognitive accuracy over unrestricted or fully restricted conditions in a lab study with 105 students.
A 14-code content model for local post-hoc AI explanations, derived from 325 user statements and validated by experts with high reliability scores.
Researchers derived 19 design guidelines for AI-supported adult learning from thematic analysis of real deployments and demonstrated their use via heuristic evaluation and an ideation tool.
EOS-Bench creates thousands of satellite scheduling test cases spanning small to large scales and evaluates multiple solver types across five performance metrics.
CF-VLA uses a coarse initialization over endpoint velocity followed by single-step refinement to achieve strong performance with low inference steps on CALVIN, LIBERO, and real-robot tasks.
InfiniLoRA decouples LoRA execution from base-model inference and reports 3.05x higher request throughput plus 54% more adapters meeting strict latency SLOs.
The first systematic review of routine computing synthesizes literature into a taxonomy of temporal, behavioral, cognitive, and variability aspects, outlining applications in health, accessibility, and adaptive support along with persistent challenges.
A Generative Flow Network framework with experience replay, exploratory policy, and physics masking samples ray paths for radio propagation up to 100x faster than exhaustive search on idealized scenarios.
FFM finds optimal fused mappings for tensor accelerators over 10,000 times faster than prior mappers while cutting energy-delay product by up to 1.8x versus hand-tuned designs.
M-ASPM decouples receiver sensitivity gains from collision exposure in LPWANs via a single shared detection channel that handles synchronization, CFO estimation, and payload channel selection across multiple payload channels.
Proposes data-aware static analysis combining data/control flow and API contracts to detect semantic faults in ML code early, shown on sample real-world notebooks.
dille detects silent semantic faults in random forest ML pipelines with 91% precision via data-informed static analysis on Kaggle notebooks, finding 12-18% of scripts affected.
A multi-backend structural gate for LLM-generated Cypher queries achieves 100% detection of parse, constraint, and schema errors at zero false positives on 1135 queries while preserving model accuracy and adding a cost planner.
Agentic iteration improves perceived quality of generated multiview genomics visualizations over direct LLM generation, but adding more specialist agents or a reviewer yields no further gains across 159 test cases.
Picid is a new modular evaluation infrastructure that enforces deterministic, leakage-safe dataset construction and unified protocols for fault detection, diagnostics, and prognostics across twelve datasets and thirteen models.
A decoupled pipeline with YOLO detection, deterministic prompt encoding, and QLoRA-adapted 1.5B LLM achieves superior structured report generation compared to monolithic VLMs on synthetic maintenance data.
K-U-KAN combines KAN feature lifting, Koopman linear dynamics, and U-KAN refinement with physical and geometric priors to reconstruct 3D dental anatomy from single panoramic radiographs, matching baselines on metrics while improving perceptual quality and halving training time.
VISOR is a VLM-based automated test oracle that evaluates robot task correctness and quality from videos while reporting its own uncertainty, tested on GPT and Gemini across four tasks and over 1000 videos with Gemini showing higher recall and GPT higher precision but low uncertainty-correctness tie
MooD introduces continuous valence-arousal modeling with VA-aware retrieval and perception-enhanced guidance for efficient, controllable affective image editing, plus a new AffectSet dataset.
Lottery BP adds randomness to belief propagation decoding and uses syndrome voting to achieve far higher accuracy on topological quantum codes while reducing reliance on expensive global decoders.
KAIROS reduces power by 27% on average (up to 39.8%) for agentic AI inference by using long-lived context to jointly manage GPU frequency, concurrency, and request routing across instances.
citing papers explorer
-
Access Timing as Scaffolding: A Reinforcement Learning Approach to GenAI in Education
A reinforcement learning agent for timing GenAI access improved post-test performance and metacognitive accuracy over unrestricted or fully restricted conditions in a lab study with 105 students.
-
Guidelines for Designing AI Technologies to Support Adult Learning
Researchers derived 19 design guidelines for AI-supported adult learning from thematic analysis of real deployments and demonstrated their use via heuristic evaluation and an ideation tool.
-
ANVIL: Analogies and Videos for Lecturers
ANVIL automates analogy-based instructional animations for computer science by chaining LLM analogy generation, screenplay structuring, manim code production with repair, and mixed human-automated evaluations.