MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking, October 2025
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
baseline 1
dataset 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5representative citing papers
ColChunk adaptively chunks visual document patches into contextual multi-vectors via clustering, cutting storage by over 90% while raising average nDCG@5 by 9 points.
DualView fuses local cross-attention and global context aggregation via adaptive gating to rerank fixed candidate sets for multi-hop QA, reporting 99.4% Top-4 Recall on MuSiQue at 4 ms latency while beating larger cross-encoders.
Back-Reveal shows that LLM agents with tool access can be backdoored via fine-tuning to exfiltrate stored user context through memory and retrieval tool calls, with multi-turn interactions enabling sustained leakage.
RRK compresses documents to multi-token embeddings for efficient listwise reranking, enabling an 8B model to achieve 3x-18x speedups over smaller models with comparable or better effectiveness.
citing papers explorer
-
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
-
Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval
ColChunk adaptively chunks visual document patches into contextual multi-vectors via clustering, cutting storage by over 90% while raising average nDCG@5 by 9 points.
-
DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking
DualView fuses local cross-attention and global context aggregation via adaptive gating to rerank fixed candidate sets for multi-hop QA, reporting 99.4% Top-4 Recall on MuSiQue at 4 ms latency while beating larger cross-encoders.
-
Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use
Back-Reveal shows that LLM agents with tool access can be backdoored via fine-tuning to exfiltrate stored user context through memory and retrieval tool calls, with multi-turn interactions enabling sustained leakage.
-
Efficient Listwise Reranking with Compressed Document Representations
RRK compresses documents to multi-token embeddings for efficient listwise reranking, enabling an 8B model to achieve 3x-18x speedups over smaller models with comparable or better effectiveness.