Pairwise scoring signals in Vision Transformer token reduction are inherently unstable due to high perturbation counts and degrade in deep layers, causing collapse, while unary signals with triage enable CATIS to retain 96.9% accuracy at 63% FLOPs reduction on ViT-Large ImageNet-1K.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
UWE is a task-agnostic bi-encoder that uses many-to-many InfoNCE and token-level soft late interaction to achieve zero-shot ranking across unseen work-related target spaces while using far fewer parameters than Qwen3-8B and improving MAP by 4.4 points.
CLSR is an end-to-end contrastive language-speech retriever using an intermediate text-like conversion step to improve retrieval of relevant segments from long audio for spoken question answering.
Directly fine-tuning the value bias (b_v) in transformer projections outperforms fine-tuning b_q or b_k for downstream performance in low-data regimes across multiple LLM architectures.
citing papers explorer
-
Why Training-Free Token Reduction Collapses: The Inherent Instability of Pairwise Scoring Signals
Pairwise scoring signals in Vision Transformer token reduction are inherently unstable due to high perturbation counts and degrade in deep layers, causing collapse, while unary signals with triage enable CATIS to retain 96.9% accuracy at 63% FLOPs reduction on ViT-Large ImageNet-1K.
-
Unified Work Embeddings: Contrastive Learning of a Bidirectional Multi-task Ranker
UWE is a task-agnostic bi-encoder that uses many-to-many InfoNCE and token-level soft late interaction to achieve zero-shot ranking across unseen work-related target spaces while using far fewer parameters than Qwen3-8B and improving MAP by 4.4 points.
-
End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering
CLSR is an end-to-end contrastive language-speech retriever using an intermediate text-like conversion step to improve retrieval of relevant segments from long audio for spoken question answering.
-
BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes
Directly fine-tuning the value bias (b_v) in transformer projections outperforms fine-tuning b_q or b_k for downstream performance in low-data regimes across multiple LLM architectures.