DICE aggregates independently encoded document chunks into a single vector to reduce evidence dilution in long-document dense retrieval, reporting gains on LongEmbed especially beyond 4k tokens.
hub
LLM2Vec: Large language models are secretly powerful text encoders
28 Pith papers cite this work, alongside 21 external citations. Polarity classification is still indexing.
28
Pith papers citing it
21
external citations · external index
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
OmniRetriever-7B uses fusion-as-teacher distillation plus Tuple-InfoNCE to improve any-to-any audio-video-text retrieval over prior open and closed models.
TWN attaches separate reasoning and embedding LoRA adapters to a frozen backbone with gradient detachment and a self-supervised gate that decides per input whether to generate CoT, achieving SOTA on MMEB-V2 with 3-5% added parameters and up to 50% fewer reasoning tokens.
LAnR unifies retrieval-augmented generation inside a single LLM by deriving dense retrieval vectors from a [PRED] token's hidden states and using entropy to adaptively stop retrieval, outperforming prior RAG on six QA benchmarks with better efficiency.
mEOL creates aligned embeddings for text, images, and SVGs using instruction-guided MLLM one-word summaries and semantic SVG rewriting, outperforming baselines on a new text-to-SVG retrieval benchmark.
LLM deobfuscation of binaries to pseudocode depends more on reasoning ability and task-specific fine-tuning than on model size, with reasoning models showing robustness across ISAs and obfuscation levels on the new BinDeObfBench.
VLM2Vec converts state-of-the-art vision-language models into universal multimodal embedders via contrastive training on the new MMEB benchmark, delivering 10-20% absolute gains over prior models on both in-distribution and out-of-distribution tasks.
LLM embeddings condition a generative transformer to enable faster convergence, better performance, and generalization to unseen LHC processes using a single model.
GraspLLM extracts dataset-agnostic structural patterns via motif contrastive learning and aligns contextual subgraphs to LLM tokens, outperforming prior LLM-based methods on TAGs especially in zero-shot settings.
EmbedFilter applies a linear filter derived from the LLM unembedding matrix to suppress high-frequency token influences in text embeddings, yielding improved zero-shot performance and inherent dimensionality reduction.
Introduces FFR task, F2RVLM and FFRS models, and MLDR dataset for retrieving coherent multi-modal dialogue fragments, reporting superior performance on single-dialogue and corpus benchmarks.
Meta-study of MTEB rankings introduces dataset-composition and ranking-scheme robustness indicators and finds only a small subset of models stay consistently strong across tasks, languages, and evaluation variations.
TechToken uses transformer embeddings of IPC codes to measure linguistic convergence in patents and predict future technological combinations.
A difficulty-aware conversational knowledge tracing framework that combines LLMs with Item Response Theory to produce interpretable student performance predictions in tutor dialogues.
LLMs exhibit mid-layer representation advantage for recommendations; MARC compresses representations modularly to reduce costs while improving performance, as shown in a large-scale online advertising deployment.
RePrompT uses recurrent prompt tuning to inject prior-visit latent states and cohort-derived population prompt tokens into LLMs, yielding better performance than pure EHR or pure LLM baselines on MIMIC clinical prediction tasks.
Parameter-efficient fine-tuning lets MLLMs serve as effective retrievers for natural-language-guided cross-view geo-localization, beating dual-encoder baselines on GeoText-1652 and CVG-Text while using far fewer trainable parameters.
InsTraj generates realistic, instruction-faithful GPS trajectories by using an LLM to parse natural-language travel intent and a multimodal diffusion transformer to produce the paths.
Semantic similarity between texts is measured by the Jeffreys divergence between the image distributions induced by conditioning a diffusion model on each text, computed via Monte-Carlo sampling of the reverse-time SDEs.
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
MedMIX combines intra-modality expert fusion, learned inter-modality fusion, and training-only large-small collaboration to deliver robust multimodal medical prediction under incomplete modalities across three benchmarks.
AFMRL uses MLLM-generated attributes in attribute-guided contrastive learning and retrieval-aware reinforcement to achieve SOTA fine-grained multimodal retrieval on e-commerce datasets.
VLM2Vec-V2 is a multimodal embedding model trained on an extended MMEB-V2 benchmark that adds video and visual document tasks and reports gains on both new and prior image benchmarks.
ModernBERT is a new bidirectional encoder model achieving SOTA performance on diverse classification and retrieval benchmarks while offering superior speed and memory efficiency for long-context inference.
citing papers explorer
-
Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation
DICE aggregates independently encoded document chunks into a single vector to reduce evidence dilution in long-document dense retrieval, reporting gains on LongEmbed especially beyond 4k tokens.
-
OmniRetriever: Any-to-Any Audio-Video-Text Retrieval via Fusion-as-Teacher Distillation
OmniRetriever-7B uses fusion-as-teacher distillation plus Tuple-InfoNCE to improve any-to-any audio-video-text retrieval over prior open and closed models.
-
Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture
TWN attaches separate reasoning and embedding LoRA adapters to a frozen backbone with gradient detachment and a self-supervised gate that decides per input whether to generate CoT, achieving SOTA on MMEB-V2 with 3-5% added parameters and up to 50% fewer reasoning tokens.
-
Latent Abstraction for Retrieval-Augmented Generation
LAnR unifies retrieval-augmented generation inside a single LLM by deriving dense retrieval vectors from a [PRED] token's hidden states and using entropy to adaptively stop retrieval, outperforming prior RAG on six QA benchmarks with better efficiency.
-
mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval
mEOL creates aligned embeddings for text, images, and SVGs using instruction-guided MLLM one-word summaries and semantic SVG rewriting, outperforming baselines on a new text-to-SVG retrieval benchmark.
-
Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation
LLM deobfuscation of binaries to pseudocode depends more on reasoning ability and task-specific fine-tuning than on model size, with reasoning models showing robustness across ISAs and obfuscation levels on the new BinDeObfBench.
-
VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
VLM2Vec converts state-of-the-art vision-language models into universal multimodal embedders via contrastive training on the new MMEB benchmark, delivering 10-20% absolute gains over prior models on both in-distribution and out-of-distribution tasks.
-
One Generator, Any Process: LLM-Conditioning for the LHC
LLM embeddings condition a generative transformer to enable faster convergence, better performance, and generalization to unseen LHC processes using a single model.
-
GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs
GraspLLM extracts dataset-agnostic structural patterns via motif contrastive learning and aligns contextual subgraphs to LLM tokens, outperforming prior LLM-based methods on TAGs especially in zero-shot settings.
-
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings
EmbedFilter applies a linear filter derived from the LLM unembedding matrix to suppress high-frequency token influences in text embeddings, yielding improved zero-shot performance and inherent dimensionality reduction.
-
Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues
Introduces FFR task, F2RVLM and FFRS models, and MLDR dataset for retrieving coherent multi-modal dialogue fragments, reporting superior performance on single-dialogue and corpus benchmarks.
-
On the Robustness of Multilingual Text Embedding Rankings Across Learning Tasks, Languages, and Benchmark Datasets
Meta-study of MTEB rankings introduces dataset-composition and ranking-scheme robustness indicators and finds only a small subset of models stay consistently strong across tasks, languages, and evaluation variations.
-
Anticipating Innovation Using Large Language Models
TechToken uses transformer embeddings of IPC codes to measure linguistic convergence in patents and predict future technological combinations.
-
Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
A difficulty-aware conversational knowledge tracing framework that combines LLMs with Item Response Theory to produce interpretable student performance predictions in tutor dialogues.
-
Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations
LLMs exhibit mid-layer representation advantage for recommendations; MARC compresses representations modularly to reduce costs while improving performance, as shown in a large-scale online advertising deployment.
-
RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models
RePrompT uses recurrent prompt tuning to inject prior-visit latent states and cohort-derived population prompt tokens into LLMs, yielding better performance than pure EHR or pure LLM baselines on MIMIC clinical prediction tasks.
-
Turning Generators into Retrievers: Unlocking MLLMs for Natural Language-Guided Geo-Localization
Parameter-efficient fine-tuning lets MLLMs serve as effective retrievers for natural-language-guided cross-view geo-localization, beating dual-encoder baselines on GeoText-1652 and CVG-Text while using far fewer trainable parameters.
-
InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories
InsTraj generates realistic, instruction-faithful GPS trajectories by using an LLM to parse natural-language travel intent and a multimodal diffusion transformer to produce the paths.
-
Conjuring Semantic Similarity
Semantic similarity between texts is measured by the Jeffreys divergence between the image distributions induced by conditioning a diffusion model on each text, computed via Monte-Carlo sampling of the reverse-time SDEs.
-
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
-
MedMIX: Modality-Internal Expert Fusion for Multimodal Medical Diagnosis
MedMIX combines intra-modality expert fusion, learned inter-modality fusion, and training-only large-small collaboration to deliver robust multimodal medical prediction under incomplete modalities across three benchmarks.
-
AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce
AFMRL uses MLLM-generated attributes in attribute-guided contrastive learning and retrieval-aware reinforcement to achieve SOTA fine-grained multimodal retrieval on e-commerce datasets.
-
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
VLM2Vec-V2 is a multimodal embedding model trained on an extended MMEB-V2 benchmark that adds video and visual document tasks and reports gains on both new and prior image benchmarks.
-
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
ModernBERT is a new bidirectional encoder model achieving SOTA performance on diverse classification and retrieval benchmarks while offering superior speed and memory efficiency for long-context inference.
-
HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval
HARNESS-LM uses teacher fine-tuning, L2 query alignment, and contrastive refinement to distill large SLM retrievers into compact models that recover 98% precision with up to 27x lower latency on Bing Ads benchmarks.
-
From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems
Coreference resolution improves retrieval relevance and QA performance in RAG systems, with mean pooling performing best and smaller models benefiting more.
-
Are Decoder-Only Large Language Models the Silver Bullet for Code Search?
Fine-tuned decoder-only LLMs achieve up to 40.4% higher MAP than UniXcoder on CoSQA+ for code search, with non-monotonic size scaling and data composition sensitivity.
- Towards Generalizable and Efficient Large-Scale Generative Recommenders