Imagen de Portada

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Warner, Benjamin, Chaffin, Antoine, Clavié, Benjamin, Weller, Orion, Hallström, Oskar, Taghadouini, Said, Gallagher, Alexis, Biswas, Raja, Ladhak, Faisal, Aarsen, Tom, Cooper, Nathan, Adams, Griffin, Howard, Jeremy, Poli, Iacopo
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
por: Clavié, Benjamin, et al.
Publicado: (2024)

It's All in The [MASK]: Simple Instruction-Tuning Enables BERT-like Masked Language Models As Generative Classifiers
por: Clavié, Benjamin, et al.
Publicado: (2025)

LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026
por: Clavié, Benjamin, et al.
Publicado: (2025)

Seq vs Seq: An Open Suite of Paired Encoders and Decoders
por: Weller, Orion, et al.
Publicado: (2025)

Towards Better Monolingual Japanese Retrievers with Multi-Vector Models
por: Clavié, Benjamin
Publicado: (2023)

rerankers: A Lightweight Python Library to Unify Ranking Methods
por: Clavié, Benjamin
Publicado: (2024)

JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources
por: Clavié, Benjamin
Publicado: (2024)

LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR
por: Taghadouini, Said, et al.
Publicado: (2026)

ReadBench: Measuring the Dense Text Visual Reading Ability of Vision-Language Models
por: Clavié, Benjamin, et al.
Publicado: (2025)

mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
por: Marone, Marc, et al.
Publicado: (2025)

NevIR: Negation in Neural Information Retrieval
por: Weller, Orion, et al.
Publicado: (2023)

AI in Architecture: Smarter and Faster Building Designs
por: Khanal, Upendra, et al.
Publicado: (2025)

Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning
por: Zhang, Li, et al.
Publicado: (2025)

STORYSUMM: Evaluating Faithfulness in Story Summarization
por: Subbiah, Melanie, et al.
Publicado: (2024)

Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report
por: Takehi, Rikiya, et al.
Publicado: (2025)

Incorporating Human Explanations for Robust Hate Speech Detection
por: Chen, Jennifer L., et al.
Publicado: (2024)

Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies
por: Clavié, Benjamin, et al.
Publicado: (2026)

Aligning Large Language Models via Fine-grained Supervision
por: Xu, Dehong, et al.
Publicado: (2024)

Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference
por: Han, Chao, et al.
Publicado: (2025)

Defending Against Disinformation Attacks in Open-Domain Question Answering
por: Weller, Orion, et al.
Publicado: (2022)

Probing the Axion-Electron Coupling with NuSTAR Observations of Galaxies
por: Ning, Orion, et al.
Publicado: (2025)

Leading Axion-Photon Sensitivity with NuSTAR Observations of M82 and M87
por: Ning, Orion, et al.
Publicado: (2024)

Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding
por: Zhao, Weilin, et al.
Publicado: (2024)

Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update
por: Almansoori, Abdulla Jasem, et al.
Publicado: (2025)

APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
por: Yang, Xinyu, et al.
Publicado: (2025)

Mashup Learning: Faster Finetuning by Remixing Past Checkpoints
por: Vaina, Sofia Maria Lo Cicero, et al.
Publicado: (2026)

U.S. Serial Services Price Index for 1997.
por: Chaffin, Nancy J.
Publicado: (1997)

Faster, Smaller, and Smarter: Task-Aware Expert Merging for Online MoE Inference
por: Han, Ziyi, et al.
Publicado: (2025)

Simple Projection Variants Improve ColBERT Performance
por: Clavié, Benjamin, et al.
Publicado: (2025)

Dichotomies Faster or Slower than exponential are Irrelevant for Skew-Product Flows
por: Jara, Néstor, et al.
Publicado: (2026)

Dated Data: Tracing Knowledge Cutoffs in Large Language Models
por: Cheng, Jeffrey, et al.
Publicado: (2024)

SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses
por: Jiang, Dongwei, et al.
Publicado: (2024)

Rank1: Test-Time Compute for Reranking in Information Retrieval
por: Weller, Orion, et al.
Publicado: (2025)

"According to ...": Prompting Language Models Improves Quoting from Pre-Training Data
por: Weller, Orion, et al.
Publicado: (2023)

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
por: Weller, Orion, et al.
Publicado: (2024)

Orthogonal Finetuning Made Scalable
por: Qiu, Zeju, et al.
Publicado: (2025)

Provably Faster Gradient Descent via Long Steps
por: Grimmer, Benjamin
Publicado: (2023)

Formal Contact Categories
por: Cooper, Benjamin
Publicado: (2015)

Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift
por: Zhang, Yi, et al.
Publicado: (2025)

Cosmological Neutron Stars Produce Diffuse Axion X-Ray Signatures
por: Ning, Orion, et al.
Publicado: (2025)