DP-SelFT improves the privacy-utility trade-off for LLM fine-tuning by selecting robust layer subsets via DP synthetic data and perturbation-matched evaluation.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
Modular curriculum learning with tier-specific adapters outperforms standard fine-tuning on complex Text-to-SQL queries in Spider and BIRD benchmarks by avoiding catastrophic forgetting.
Speculative precomputation of foundation-model user–item embeddings decouples heavy inference from the serving path and yields 0.67% revenue gain at Meta ads scale.
VaaWIT proposes DSAM and VAA modules to adapt LLMs for multilingual web image translation, claiming outperformance over open-source baselines on benchmarks.
CDGLT achieves SOTA on MET-Meme for multimodal metaphor identification by using SLERP-based concept drift and prompt-adapted LayerNorm tuning with reduced compute.
DAT combines a small-large model cascade with fine-tuning and bandwidth-aware multi-stream transmission to deliver high-accuracy event recognition and low-latency alerts for video streams in edge-cloud systems.
citing papers explorer
-
DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
DP-SelFT improves the privacy-utility trade-off for LLM fine-tuning by selecting robust layer subsets via DP synthetic data and perturbation-matched evaluation.
-
LeGo-Code: Can Modular Curriculum Learning Advance Complex Code Generation? Insights from Text-to-SQL
Modular curriculum learning with tier-specific adapters outperforms standard fine-tuning on complex Text-to-SQL queries in Spider and BIRD benchmarks by avoiding catastrophic forgetting.
-
SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling
Speculative precomputation of foundation-model user–item embeddings decouples heavy inference from the serving path and yields 0.67% revenue gain at Meta ads scale.
-
VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation
VaaWIT proposes DSAM and VAA modules to adapt LLMs for multilingual web image translation, claiming outperformance over open-source baselines on benchmarks.
-
Concept Drift Guided LayerNorm Tuning for Efficient Multimodal Metaphor Identification
CDGLT achieves SOTA on MET-Meme for multimodal metaphor identification by using SLERP-based concept drift and prompt-adapted LayerNorm tuning with reduced compute.
-
DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems
DAT combines a small-large model cascade with fine-tuning and bandwidth-aware multi-stream transmission to deliver high-accuracy event recognition and low-latency alerts for video streams in edge-cloud systems.