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 models are unsupervised multitask learners
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
GQKAE uses quantum-inspired Kolmogorov-Arnold networks to reduce parameters by 66% in generative quantum eigensolvers while achieving chemical accuracy on H4, N2, LiH, and other molecules.
ProjRes achieves near-100% accuracy in membership inference on FedLLMs by measuring projection residuals of hidden embeddings on gradient subspaces, outperforming prior methods by up to 75.75% even under differential privacy.
CoT prompting in LLM4Code shows mixed robustness that depends on model family, task structure, and perturbations destabilizing structural anchors, leading to trajectory deformations like lengthening, branching, and simplification.
MetaKE unifies knowledge editing stages via bi-level optimization and a structural gradient proxy to improve the accuracy-editability trade-off over prior methods.
Diffusion LLMs can act as their own efficiency teachers by using revokable parallel decoding to identify reliable token orders and then distilling those orders into the model parameters for faster inference.
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.
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.
LLaDA-V is a diffusion-based multimodal large language model that reaches competitive or state-of-the-art results on visual instruction tasks while using a non-autoregressive architecture.
This is the first survey on vision-language-action models, providing a taxonomy across three lines, plus summaries of datasets, simulators, benchmarks, challenges, and future directions in embodied AI.
Reveals hidden human-like spans in machine-generated texts that raise detection complexity and proposes a stacked enhancement framework with hard-EM optimization to improve detectors across LLMs.
A multi-level framework that models local and global relations among token detection scores to improve machine-generated text detection with low overhead.
BerLU constructs a C1-differentiable activation with Lipschitz constant 1 via Bernstein polynomial approximation, showing better performance and efficiency than baselines on image classification with ViTs and CNNs.
ADAM uses personality-guided LLM augmentation and cross-lingual attention distillation to raise balanced accuracy on multilingual personality recognition to 0.6332 on Essays and 0.7448 on Kaggle, outperforming standard BCE loss.
MeZO enables larger models for on-device fine-tuning by estimating gradients via forward passes only, with theoretical size estimates and numerical results showing accuracy benefits when wall-clock time is sufficient.
RadarPLM adapts PLMs for marine radar target detection with lightweight adaptation and selective fine-tuning based on online learning values, reporting at least 6.35% average detection gains in low SCR conditions.
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.
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.
-
Generative Quantum-inspired Kolmogorov-Arnold Eigensolver
GQKAE uses quantum-inspired Kolmogorov-Arnold networks to reduce parameters by 66% in generative quantum eigensolvers while achieving chemical accuracy on H4, N2, LiH, and other molecules.
-
Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approach
ProjRes achieves near-100% accuracy in membership inference on FedLLMs by measuring projection residuals of hidden embeddings on gradient subspaces, outperforming prior methods by up to 75.75% even under differential privacy.
-
Structural Anchors and Reasoning Fragility:Understanding CoT Robustness in LLM4Code
CoT prompting in LLM4Code shows mixed robustness that depends on model family, task structure, and perturbations destabilizing structural anchors, leading to trajectory deformations like lengthening, branching, and simplification.
-
MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-off
MetaKE unifies knowledge editing stages via bi-level optimization and a structural gradient proxy to improve the accuracy-editability trade-off over prior methods.
-
Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers
Diffusion LLMs can act as their own efficiency teachers by using revokable parallel decoding to identify reliable token orders and then distilling those orders into the model parameters for faster inference.
-
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.
-
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.
-
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
LLaDA-V is a diffusion-based multimodal large language model that reaches competitive or state-of-the-art results on visual instruction tasks while using a non-autoregressive architecture.
-
A Survey on Vision-Language-Action Models for Embodied AI
This is the first survey on vision-language-action models, providing a taxonomy across three lines, plus summaries of datasets, simulators, benchmarks, challenges, and future directions in embodied AI.
-
Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement
Reveals hidden human-like spans in machine-generated texts that raise detection complexity and proposes a stacked enhancement framework with hard-EM optimization to improve detectors across LLMs.
-
Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detection
A multi-level framework that models local and global relations among token detection scores to improve machine-generated text detection with low overhead.
-
Universal Smoothness via Bernstein Polynomials: A Constructive Approximation Approach for Activation Functions
BerLU constructs a C1-differentiable activation with Lipschitz constant 1 via Bernstein polynomial approximation, showing better performance and efficiency than baselines on image classification with ViTs and CNNs.
-
Cross-Lingual Attention Distillation with Personality-Informed Generative Augmentation for Multilingual Personality Recognition
ADAM uses personality-guided LLM augmentation and cross-lingual attention distillation to raise balanced accuracy on multilingual personality recognition to 0.6332 on Essays and 0.7448 on Kaggle, outperforming standard BCE loss.
-
On-Device Fine-Tuning via Backprop-Free Zeroth-Order Optimization
MeZO enables larger models for on-device fine-tuning by estimating gradients via forward passes only, with theoretical size estimates and numerical results showing accuracy benefits when wall-clock time is sufficient.
-
RadarPLM: Adapting Pre-trained Language Models for Marine Radar Target Detection by Selective Fine-tuning
RadarPLM adapts PLMs for marine radar target detection with lightweight adaptation and selective fine-tuning based on online learning values, reporting at least 6.35% average detection gains in low SCR conditions.
-
Large Language Model-Brained GUI Agents: A Survey
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
-
Low-Rank Adaptation Redux for Large Models
An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.