GRAM selectively trains auxiliary modules so that ablating one at inference removes a targeted capability while preserving the rest, closely tracking data-filtered models at 5x lower cost across 5 capability profiles.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
Compiling repeated SOP nodes into environment-grounded, versioned tools cuts production p50 latency by 42% and end-to-end error rate by up to 53% in a 44-node fulfillment-center alarm-triage agent.
Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.
Optimizer choice during LLM fine-tuning produces up to 7x variation in emergent misalignment rates, with spectral regularization on LoRA adapters substantially mitigating misalignment for prone optimizers.
Gradient-based proportional LoRA rank allocation under GRPO reduces accuracy by 4.5 points versus uniform allocation because GRPO gradients are flatter across layers and non-uniform ranks amplify importance differences.
LLM-backed audio-text encoders match M2D-CLAP on caption retrieval but substantially improve text-to-text retrieval and hard-negative discrimination under user-intent queries.
Llama 3.1 8B fine-tuned with calibrated 5% synthetic data augmentation reaches 0.6234 F1-macro on multi-class toxicity detection in gaming chat and places fourth among 35 teams.
citing papers explorer
-
Modular Pretraining Enables Access Control
GRAM selectively trains auxiliary modules so that ablating one at inference removes a targeted capability while preserving the rest, closely tracking data-filtered models at 5x lower cost across 5 capability profiles.
-
Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems
Compiling repeated SOP nodes into environment-grounded, versioned tools cuts production p50 latency by 42% and end-to-end error rate by up to 53% in a 44-node fulfillment-center alarm-triage agent.
-
Multi-Objective Exploration and Preference Optimization via Mutual Information
Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.
-
Evil Spectra: How Optimisers can Amplify or Suppress Emergent Misalignment
Optimizer choice during LLM fine-tuning produces up to 7x variation in emergent misalignment rates, with spectral regularization on LoRA adapters substantially mitigating misalignment for prone optimizers.
-
Gradient-Based LoRA Rank Allocation Under GRPO: An Empirical Study
Gradient-based proportional LoRA rank allocation under GRPO reduces accuracy by 4.5 points versus uniform allocation because GRPO gradients are flatter across layers and non-uniform ranks amplify importance differences.
-
Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval
LLM-backed audio-text encoders match M2D-CLAP on caption retrieval but substantially improve text-to-text retrieval and hard-negative discrimination under user-intent queries.
-
PSK@EEUCA 2026: Fine-Tuning Large Language Models with Synthetic Data Augmentation for Multi-Class Toxicity Detection in Gaming Chat
Llama 3.1 8B fine-tuned with calibrated 5% synthetic data augmentation reaches 0.6234 F1-macro on multi-class toxicity detection in gaming chat and places fourth among 35 teams.