QLAM extends state-space models with quantum superposition in the hidden state for linear-time long-sequence modeling and reports consistent gains over RNN and transformer baselines on sequential image tasks.
hub
Language mod- els are few-shot learners
27 Pith papers cite this work. Polarity classification is still indexing.
27
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
verdicts
UNVERDICTED 27roles
background 4polarities
background 4representative citing papers
LoRM is a self-supervised framework that models multi-modal rotating machinery signals as token sequences for prediction with fine-tuned language models, using prediction errors to monitor machine health in real time.
GRAIL trains graph predictors via imitation learning by modeling generation as sequential decisions on partial graph embeddings, matching or exceeding prior methods on 18 benchmarks.
D³ETOR combines debate-enhanced pseudo labeling from SAM with frequency-aware progressive debiasing in FADeNet to achieve state-of-the-art weakly-supervised camouflaged object detection using scribbles.
BELIEF improves closed-set biomedical QA by converting documents to structured evidence objects and fusing D-S symbolic belief estimation with LLM inference through reliability-aware arbitration.
PrivScope enforces task-scoped disclosure at the local-cloud boundary in hybrid agents, eliminating profile leakage and halving re-identification risk on medical workflows while preserving task success.
FusionCIM is a fusion-driven CIM accelerator for LLM inference that maps QKT to IP-CIM and PV to OP-CIM, uses QO-stationary dataflow, and applies pattern-aware online softmax, delivering up to 3.86x energy savings and 1.98x speedup on LLaMA-3 at 29.4 TOPS/W.
Behavior Forest decouples multi-constraint travel planning into parallel behavior trees with LLM nodes and global coordination, yielding 6.67% and 11.82% gains over prior methods on two benchmarks.
PARM adapts reward models to multi-stage LLM pipelines via pipeline data and direct preference optimization, improving execution rate and solving accuracy on optimization benchmarks and showing transfer to GSM8K.
A precision-aware predictor for distributed training time achieves 9.8% MAPE across precision settings, compared to errors up to 147.85% when precision is ignored.
PlanGuard cuts indirect prompt injection attack success rate to 0% on the InjecAgent benchmark by verifying agent actions against a user-instruction-only plan while keeping false positives at 1.49%.
SLaB compresses LLM weights via sparse-lowrank-binary decomposition guided by activation-aware scores, achieving up to 36% lower perplexity than prior methods at 50% compression on Llama models.
HIL-CBM is a hierarchical label-free concept bottleneck model that improves classification accuracy and explanation quality over prior single-level CBMs using a visual consistency loss and dual heads.
LLMs using in-context learning and fine-tuning on listener experiment data generate equalization settings that align better with population preferences than random sampling or static presets.
A hybrid two-stage framework pairs a discriminative front-end for interference suppression with a generative decoder-only LM back-end to improve perceptual quality and speaker consistency in target speaker extraction and speech enhancement.
GUIde uses AI to translate man pages into graphical interface specifications for command line tools, evaluated on a corpus of real commands.
DeRelayL is a proposed sustainable decentralized learning paradigm where permissionless participants relay-train and share models via designed incentives, backed by theoretical analysis and simulations.
Chunk-as-a-Service with the UCOSA online algorithm enables budget-constrained selection of prompts for chunk enrichment in RAG, outperforming random selection by 52% on a combined performance metric and delivering higher performance-to-budget ratios than standard RaaS.
Selective state-space models achieve online filtering for unknown systems from the same class with generalization bounds derived under appropriate assumptions.
The paper introduces an agentic AI platform to train and support recovered soldiers as peer facilitators providing mental health triage and interventions in austere battlefield environments.
MAGIC-HMO is a multi-agent framework that treats Chinese short-form creative NLG as heterogeneous multi-objective optimization over personalized constraints plus explanation reliability and outperforms baselines on a baby-naming benchmark.
LLMs recover interpretable topic structures via attention and achieve competitive topic modeling performance as long-context generators.
CMBAgent achieves high accuracy on well-specified astrophysical tasks with context but generates silent, plausible-yet-incorrect outputs on reasoning-challenging problems, with no self-diagnosis of inconsistencies.
AICCE combines RAG-based retrieval of protocol specs with dual LLM pipelines for debate-driven explanations or fast script execution, reporting up to 99% accuracy on IPv6 samples.
citing papers explorer
-
QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling
QLAM extends state-space models with quantum superposition in the hidden state for linear-time long-sequence modeling and reports consistent gains over RNN and transformer baselines on sequential image tasks.
-
LoRM: Learning the Language of Rotating Machinery for Self-Supervised Condition Monitoring
LoRM is a self-supervised framework that models multi-modal rotating machinery signals as token sequences for prediction with fine-tuned language models, using prediction errors to monitor machine health in real time.
-
Building Deep Graph Predictors with Graph Imitation Learning
GRAIL trains graph predictors via imitation learning by modeling generation as sequential decisions on partial graph embeddings, matching or exceeding prior methods on 18 benchmarks.
-
Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotations
D³ETOR combines debate-enhanced pseudo labeling from SAM with frequency-aware progressive debiasing in FADeNet to achieve state-of-the-art weakly-supervised camouflaged object detection using scribbles.
-
BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering
BELIEF improves closed-set biomedical QA by converting documents to structured evidence objects and fusing D-S symbolic belief estimation with LLM inference through reliability-aware arbitration.
-
PrivScope: Task-scoped Disclosure Control for Hybrid Agentic Systems
PrivScope enforces task-scoped disclosure at the local-cloud boundary in hybrid agents, eliminating profile leakage and halving re-identification risk on medical workflows while preserving task success.
-
FusionCIM: Accelerating LLM Inference with Fusion-Driven Computing-in-Memory Architecture
FusionCIM is a fusion-driven CIM accelerator for LLM inference that maps QKT to IP-CIM and PV to OP-CIM, uses QO-stationary dataflow, and applies pattern-aware online softmax, delivering up to 3.86x energy savings and 1.98x speedup on LLaMA-3 at 29.4 TOPS/W.
-
Decoupled Travel Planning with Behavior Forest
Behavior Forest decouples multi-constraint travel planning into parallel behavior trees with LLM nodes and global coordination, yielding 6.67% and 11.82% gains over prior methods on two benchmarks.
-
PARM: Pipeline-Adapted Reward Model
PARM adapts reward models to multi-stage LLM pipelines via pipeline data and direct preference optimization, improving execution rate and solving accuracy on optimization benchmarks and showing transfer to GSM8K.
-
Training Time Prediction for Mixed Precision-based Distributed Training
A precision-aware predictor for distributed training time achieves 9.8% MAPE across precision settings, compared to errors up to 147.85% when precision is ignored.
-
PlanGuard: Defending Agents against Indirect Prompt Injection via Planning-based Consistency Verification
PlanGuard cuts indirect prompt injection attack success rate to 0% on the InjecAgent benchmark by verifying agent actions against a user-instruction-only plan while keeping false positives at 1.49%.
-
SLaB: Sparse-Lowrank-Binary Decomposition for Efficient Large Language Models
SLaB compresses LLM weights via sparse-lowrank-binary decomposition guided by activation-aware scores, achieving up to 36% lower perplexity than prior methods at 50% compression on Llama models.
-
Hierarchical, Interpretable, Label-Free Concept Bottleneck Model
HIL-CBM is a hierarchical label-free concept bottleneck model that improves classification accuracy and explanation quality over prior single-level CBMs using a visual consistency loss and dual heads.
-
One Prompt, Many Sounds: Modeling Listener Variability in LLM-Based Equalization
LLMs using in-context learning and fine-tuning on listener experiment data generate equalization settings that align better with population preferences than random sampling or static presets.
-
Discriminative-Generative Target Speaker Extraction with Decoder-Only Language Models
A hybrid two-stage framework pairs a discriminative front-end for interference suppression with a generative decoder-only LM back-end to improve perceptual quality and speaker consistency in target speaker extraction and speech enhancement.
-
The Command Line GUIde: Graphical Interfaces from Man Pages via AI
GUIde uses AI to translate man pages into graphical interface specifications for command line tools, evaluated on a corpus of real commands.
-
DeRelayL: Sustainable Decentralized Relay Learning
DeRelayL is a proposed sustainable decentralized learning paradigm where permissionless participants relay-train and share models via designed incentives, backed by theoretical analysis and simulations.
-
Budget-Constrained Online Retrieval-Augmented Generation: The Chunk-as-a-Service Model
Chunk-as-a-Service with the UCOSA online algorithm enables budget-constrained selection of prompts for chunk enrichment in RAG, outperforming random selection by 52% on a combined performance metric and delivering higher performance-to-budget ratios than standard RaaS.
-
On the Generalization Properties of Selective State-Space Models for Filtering Tasks for Unknown Systems
Selective state-space models achieve online filtering for unknown systems from the same class with generalization bounds derived under appropriate assumptions.
-
Train the Trainers -- An Agentic AI Framework for Peer-Based Mental Health Support in Battlefield Environments
The paper introduces an agentic AI platform to train and support recovered soldiers as peer facilitators providing mental health triage and interventions in austere battlefield environments.
-
Chinese Short-Form Creative Content Generation via Explanation-Oriented Multi-Objective Optimization
MAGIC-HMO is a multi-agent framework that treats Chinese short-form creative NLG as heterogeneous multi-objective optimization over personalized constraints plus explanation reliability and outperforms baselines on a baby-naming benchmark.
-
LLM as Attention-Informed NTM and Topic Modeling as long-input Generation: Interpretability and long-Context Capability
LLMs recover interpretable topic structures via attention and achieve competitive topic modeling performance as long-context generators.
-
Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows
CMBAgent achieves high accuracy on well-specified astrophysical tasks with context but generates silent, plausible-yet-incorrect outputs on reasoning-challenging problems, with no self-diagnosis of inconsistencies.
-
AICCE: AI Driven Compliance Checker Engine
AICCE combines RAG-based retrieval of protocol specs with dual LLM pipelines for debate-driven explanations or fast script execution, reporting up to 99% accuracy on IPv6 samples.
-
VeriInteresting: An Empirical Study of Model Prompt Interactions in Verilog Code Generation
Empirical study identifies patterns in how model classes respond to structured prompts, optimization, and other techniques across two Verilog benchmarks.
-
Threat Modelling using Domain-Adapted Language Models: Empirical Evaluation and Insights
Domain-adapted LLMs and SLMs do not consistently outperform general models on STRIDE threat classification for 5G, with decoding strategies and model scale affecting validity but gains remaining insufficient for reliable use.
-
Redefining End-of-Life: Intelligent Automation for Electronics Remanufacturing Systems
A literature review of intelligent automation approaches using robotics, AI, and control for disassembly, inspection, sorting, and reprocessing of end-of-life electronics.