A corpus augmentation pipeline using CTC clip extraction, LLM-generated gloss sentences, and random video stitching improves BLEU-4 by 2.92 on the GFSLT-VLP baseline for sign language translation.
Multilingual translation with extensible multilingual pretraining and finetuning
8 Pith papers cite this work, alongside 153 external citations. Polarity classification is still indexing.
8
Pith papers citing it
153
external citations · external index
representative citing papers
LongBEL improves biomedical entity linking consistency by combining full-document context with memory of previous predictions trained via cross-validation rather than gold labels.
A pair selection strategy based on negative similarity dynamics strengthens contrastive supervision in gloss-free sign language translation by reducing noisy negatives.
Benign multilingual fine-tuning causes language-specific safety drifts with adversarial compliance rates rising up to four-fold, decoupled from capability gains.
A modified divergence decouples top-K teacher probabilities from the distribution tail during distillation, yielding competitive performance on decoder models with standard compute.
Pruning small-magnitude weights from pre-trained LLMs causes monotonic irreversible performance degradation on difficult downstream tasks, supporting the Junk DNA Hypothesis that these weights hold essential knowledge.
Machine interpreting should shift from fidelity metrics to three design priorities—agency, grounding, and experience—drawn from interpreting studies to close the usability gap with human-mediated communication.
SLO-Guard, a crash-aware two-phase autotuner for vLLM serving, achieves no best-latency improvement over random search but demonstrates more consistent budget allocation across 150 trials on Qwen2-1.5B/A100.
citing papers explorer
-
Corpus Augmentation for Sign Language Translation via LLM-Guided Video Stitching
A corpus augmentation pipeline using CTC clip extraction, LLM-generated gloss sentences, and random video stitching improves BLEU-4 by 2.92 on the GFSLT-VLP baseline for sign language translation.
-
LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking
LongBEL improves biomedical entity linking consistency by combining full-document context with memory of previous predictions trained via cross-validation rather than gold labels.
-
Selective Contrastive Learning For Gloss Free Sign Language Translation
A pair selection strategy based on negative similarity dynamics strengthens contrastive supervision in gloss-free sign language translation by reducing noisy negatives.
-
The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning
Benign multilingual fine-tuning causes language-specific safety drifts with adversarial compliance rates rising up to four-fold, decoupled from capability gains.
-
Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation
A modified divergence decouples top-K teacher probabilities from the distribution tail during distillation, yielding competitive performance on decoder models with standard compute.
-
Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs "Difficult" Downstream Tasks in LLMs
Pruning small-magnitude weights from pre-trained LLMs causes monotonic irreversible performance degradation on difficult downstream tasks, supporting the Junk DNA Hypothesis that these weights hold essential knowledge.
-
Bridging the Usability Gap: Lessons from Interpreting Studies for Machine Interpreting Design
Machine interpreting should shift from fidelity metrics to three design priorities—agency, grounding, and experience—drawn from interpreting studies to close the usability gap with human-mediated communication.
-
Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining
SLO-Guard, a crash-aware two-phase autotuner for vLLM serving, achieves no best-latency improvement over random search but demonstrates more consistent budget allocation across 150 trials on Qwen2-1.5B/A100.