Base model text evades AI detectors better than instruction-tuned text, and the HIP method strengthens this trade-off across model sizes.
hub
Advances in neural information processing systems , volume=
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
other 1
citation-polarity summary
years
2026 13roles
other 1polarities
unclear 1representative citing papers
ENMP prunes negative LoRA modules via evolutionary search to boost merging performance to new state-of-the-art levels across language and vision tasks.
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
PERSA combines RLHF with selective parameter-efficient updates to top transformer layers, raising style alignment scores from 35% to 96% on code feedback benchmarks while holding correctness near 100%.
AGoQ delivers up to 52% lower memory use and 1.34x faster training for 8B-32B LLaMA models by using near-4-bit adaptive activations and 8-bit gradients while preserving pretraining convergence and downstream accuracy.
Small LLMs under 2B parameters achieve better economic break-even, energy efficiency, and hardware density than larger models on legacy GPUs for industrial tasks.
AdaLeZO uses a non-stationary multi-armed bandit to adaptively allocate perturbation budget across layers in zeroth-order optimization and applies inverse probability weighting to reduce variance while preserving unbiased gradients, delivering 1.7x-3.0x wall-clock speedup on LLaMA and OPT models.
TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.
FreqAdapter adapts multimodal models by text-guided multi-scale fine-tuning in the frequency domain, claiming better performance and efficiency than signal-space PEFT methods.
Augmenting commonsense knowledge corpora with negation produces over 2M new triples that benefit LLM negation understanding when used for pre-training.
Fine-tuned 8B LLMs produce children's English reading stories with better difficulty control and safety than zero-shot GPT-4o and Llama 3.3 70B.
A framework combines multi-LoRA runtime switching, multi-stream stylistic decoding, and Dynamic Self-Speculative Decoding with INT4 quantization to achieve 4-6x memory and latency gains for on-device inference of a one-for-all foundational LLM on Qualcomm chipsets.
A lightweight multilingual encoder system with joint training and adaptive ensemble achieves top-half rankings across datasets in SemEval-2026 dimensional aspect sentiment regression.
citing papers explorer
-
Base Models Look Human To AI Detectors
Base model text evades AI detectors better than instruction-tuned text, and the HIP method strengthens this trade-off across model sizes.
-
Evolutionary Negative Module Pruning for Better LoRA Merging
ENMP prunes negative LoRA modules via evolutionary search to boost merging performance to new state-of-the-art levels across language and vision tasks.
-
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
-
PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs
PERSA combines RLHF with selective parameter-efficient updates to top transformer layers, raising style alignment scores from 35% to 96% on code feedback benchmarks while holding correctness near 100%.
-
AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs
AGoQ delivers up to 52% lower memory use and 1.34x faster training for 8B-32B LLaMA models by using near-4-bit adaptive activations and 8-bit gradients while preserving pretraining convergence and downstream accuracy.
-
Are Large Language Models Economically Viable for Industry Deployment?
Small LLMs under 2B parameters achieve better economic break-even, energy efficiency, and hardware density than larger models on legacy GPUs for industrial tasks.
-
Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling
AdaLeZO uses a non-stationary multi-armed bandit to adaptively allocate perturbation budget across layers in zeroth-order optimization and applies inverse probability weighting to reduce variance while preserving unbiased gradients, delivering 1.7x-3.0x wall-clock speedup on LLaMA and OPT models.
-
TLoRA: Task-aware Low Rank Adaptation of Large Language Models
TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.
-
Text-Guided Multi-Scale Frequency Representation Adaptation
FreqAdapter adapts multimodal models by text-guided multi-scale fine-tuning in the frequency domain, claiming better performance and efficiency than signal-space PEFT methods.
-
Commonsense Knowledge with Negation: A Resource to Enhance Negation Understanding
Augmenting commonsense knowledge corpora with negation produces over 2M new triples that benefit LLM negation understanding when used for pre-training.
-
Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety
Fine-tuned 8B LLMs produce children's English reading stories with better difficulty control and safety than zero-shot GPT-4o and Llama 3.3 70B.
-
Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM
A framework combines multi-LoRA runtime switching, multi-stream stylistic decoding, and Dynamic Self-Speculative Decoding with INT4 quantization to achieve 4-6x memory and latency gains for on-device inference of a one-for-all foundational LLM on Qualcomm chipsets.
-
ICT-NLP at SemEval-2026 Task 3: Less Is More -- Multilingual Encoder with Joint Training and Adaptive Ensemble for Dimensional Aspect Sentiment Regression
A lightweight multilingual encoder system with joint training and adaptive ensemble achieves top-half rankings across datasets in SemEval-2026 dimensional aspect sentiment regression.