Chunk

Follow this topic Ask about this topic

Recent momentum

-70%

3 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

3 new papers

A weekly snapshot of new work published in Chunk.

54 papers

Latest in Chunk

Open your feed →

Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure
Sep 17, 2026Zofia SmoleńSpreadsheets Chunk
Fetch My Beer: Synthetic-to-real Hierarchical Policy for Smooth Pick-and-place
Sep 16, 2026Yingyue Li, Chenyangguang Zhang, Ruida Zhang +3Real-World Manipulation Tasks Imitation Learning
Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking
Sep 14, 2026Xiaotian Wang, Youyuan Lin, Zhan Shen +1Chunk Training-Inference Mismatch
RouteRelay: Event-Triggered Cross-Layer Route Reuse for Efficient Dynamic Sparse Attention
Sep 7, 2026Bin Li, Sisi Liu, Chenyang Hu +3Dynamic Sparse Attention Adaptive Routing
Enhancing Financial Question Answering: A Novel Benchmark Dataset of Banks' financial statements
Sep 3, 2026Arianna Miola, Bruno Spaccavento, Lorenzo Silotto +2Finance Domain Multi-Hop Question Answering Benchmarks
Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation
Aug 31, 2026Riya Ahuja, Tim Kacprowski, Roya Shiasi SardoabiBiomedical Text Chunk
Withholding the Completing Chunk: Deterministic Pair-Completion Guardrails for Streaming LLM Output
Aug 10, 2026Christopher M. FrostLarge Language Model Safety Danger Recognition
ZeroLock: Concurrent Memory-Efficient LLM Training via Modular Update Decoupling
Aug 8, 2026Wentao Dai, Xuanran Li, Yuxiang Zhang +2Parallel Locks
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
Aug 6, 2026Sagar Tamang, Ayush Vyas, Tabarakul HazarikaChunk Top-K
Right Reset: Chunking by Prefix Removal
Aug 5, 2026Mike VegetoChunk Removal
Beyond Global Latents: Chunk-Based Sparse Grid VAE for Scalable 3D Modeling
Aug 3, 2026Kaiyi Zhang, Zhihao Liang, Haolin Liu +8Voxel 3D Reconstruction
Studying quantization trade-offs for efficient inference deployment in machine translation
Jul 31, 2026Jim Zhao, Sohir Maskey, Koen Oostermeijer +2Large Language Model Quantization LLM Inference Efficiency
Cross-Attention Calibrated Deduplication for Retrieval-Augmented Generation System
Jul 27, 2026Phuong Le Huy, Nam H. Nguyen, Quan V. DangRetrieval-Augmented Generation Systems Semantic Deduplication
Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms
Jul 23, 2026Abu Tyeb Azad, Fahim Ahmed, Ishita Sur Apan +7Bangla Chunk
Offline RL with Hierarchical Action Chunking
Jul 23, 2026Ahad JawaidGoal-Conditioned Reinforcement Learning Offline Reinforcement Learning
HPD-Parsing: Hierarchical Parallel Document Parsing
Jul 21, 2026Shu Wei, Jingjing Wu, Lingshu Zhang +10Parallel Next-Token Prediction
SUNTA: Hierarchical Video Prediction with Surprise-based Chunking
Jul 2, 2026Tomoshi Iiyama, Masahiro Suzuki, Yutaka MatsuoFuture Video Prediction Long-Horizon Forecasting
Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts
Jul 2, 2026Valentin J. J. Kreileder, Johannes Reisinger, Andreas FischerRetrieval-Augmented Generation Systems Chunk
Start Right, Arrive Right: Asynchronous Execution via Initial Noise Selection
Jun 18, 2026Trong-Bao Ho, Quang-Tan Nguyen, Thien-Loc Ha +7Action Chunks Asynchronous Execution
MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval
Jun 16, 2026Amirhossein Abaskohi, Raymond Li, Gaetano Cimino +3Longbench Chunk
SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
Jun 15, 2026Nathanaël LangloisRetrieval-Augmented Generation Systems Chunk
Dynamic Execution Horizon Prediction for Chunk-based Robot Policies
Jun 9, 2026Yuchi Zhao, Miroslav Bogdanovic, Arjun Sohal +5Long-Horizon Planning Robot Policies
When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines
Jun 9, 2026Xi Nie, Hongwei Li, Shenghao Wu +3Data Poisoning Retrieval-Augmented Generation Systems
C $^3$ ache: Accelerating World Action Models with Cross Inference Chunk CacheC^3ache: Accelerating World Action Models with Cross Inference Chunk Cache
Jun 8, 2026Weisen Zhao, Lam Nguyen, Zhicong Lu +1Efficient World-Action Model World Models
Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies
Jun 2, 2026Xiangdong Feng, Yuxuan Cheng, Chen Shi +5Action Chunks Dynamic Replanning
Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics
May 31, 2026Bole Ma, Jan Eitzinger, Harald Köstler +1Dynamic Sparse Attention Kv-Cache Blocks
Chunking Methods on Retrieval-Augmented Generation - Effectiveness Evaluation Against Computational Cost and Limitations
May 30, 2026Mateusz Śmigielski, Michał Rajkowski, Mateusz Zbrocki +5Chunk Retrieval-Augmented Generation Systems
Adaptive Targeted Dynamic Chunking for Tokenization-Free Hierarchical Model
May 28, 2026Thang Dang, Akira Nakagawa, Kenichi Kobayashi +1Token Compression Context Compression
SEEK: Semantic Evidence Extraction via Adaptive ChunKing for Multilingual Fact-Checking
May 26, 2026Gaurav Kumar, Babu Kumar, Ayush Garg +2Multilingual Fact-Checking Incomplete Evidence
Action-Prior Denoising for Smooth Real-Time Chunking
May 25, 2026Dongyang Liu, Zhaowen Zheng, Yu Sun +3Action Chunks Chunk
MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing
May 24, 2026Bangrui Xu, Ziyang Miao, Xuanhe Zhou +8Deepseek-Ocr Optical Character Recognition
Learning High-Frequency Continuous Action Chunks in Latent Space
May 24, 2026Kunyun Wang, Yuhang Zheng, Yupeng Zheng +2Action Chunks Generalizable Robotic Manipulations
Smoother Action Chunking Flow Policy via Prior-Corrected Orthogonal Trust-Region Guidance
May 23, 2026Kai Fang, Hailong Pei, Xuemin ChiAction Chunks Neural Guidance
Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents
May 21, 2026Sovandara Chhoun, Pichdara Po, Sereiwathna Ros +2Chunk Low-Resource Languages
ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning
May 20, 2026Yongkang Liu, Zijing Wang, Mengjie Zhao +7Chunk
Chunking German Legal Code
May 19, 2026Max Prior, Natalia Milanova, Andreas SchultzLegal Domain Chunk
Agentic Chunking and Bayesian De-chunking of AI Generated Fuzzy Cognitive Maps: A Model of the Thucydides Trap
May 18, 2026Akash Kumar Panda, Olaoluwa Adigun, Bart KoskoCognitive Map Reasoning Graphs
FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy
May 15, 2026Qian He, Zhenshuo Yang, Wenqi Liang +3Visuomotor Policy Conditional Flow Matching
Dynamic Chunking for Diffusion Language Models
May 15, 2026Yichen Zhu, Xiaoming Shi, Peng Zhao +3Diffusion Language Models Chunk
KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference
May 12, 2026Alireza Nadali, Patrick Cooper, Ashutosh Trivedi +1Efficient Long-Context Inference Key-Value Cache
OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models
May 12, 2026Yuchen Deng, Zidang Cai, Hai-Tao Zheng +3Audio-Visual Reasoning Token Compression
Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning
May 7, 2026Nandiraju Gireesh, Yuanliang Ju, He WangAction Chunks Off-Policy Evaluation
Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation
May 1, 2026Pooja Guttal, Varun Magotra, Vasudeva Mahavishnu +3Chunk Tabular Data
SG-UniBuc-NLP at SemEval-2026 Task 6: Multi-Head RoBERTa with Chunking for Long-Context Evasion Detection
Apr 29, 2026Gabriel Stefan, Sergiu NisioiNatural Language Processing Tasks Chunk
Query-Adaptive Semantic Chunking for Retrieval-Augmented Generation: A Dynamic Strategy with Contextual Window Expansion
Apr 29, 2026Mudit RastogiRetrieval-Augmented Generation Systems Chunk
Budget-Constrained Online Retrieval-Augmented Generation: The Chunk-as-a-Service Model
Apr 28, 2026Shawqi Al-Maliki, Ammar Gharaibeh, Mohamed Rahouti +4Cost-Aware Chunk
DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors
Apr 27, 2026Pengcheng Wang, Kaiwen Hong, Chensheng Peng +4Diffusion Policies Action Chunks
Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering
Apr 27, 2026Daria Berdyugina, Anaëlle Cohen, Yohann RioualChunk Retrieval-Augmented Generation Systems
CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents
Apr 17, 2026Hyunseok Park, Jihyeon Kim, Jongeun Kim +1Retrieval-Augmented Generation Systems Chunk
M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models
Apr 17, 2026Joongmin Shin, Jeongbae Park, Jaehyung Seo +1Multimodal Documents Chunk
DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression
Mar 15, 2026Bingzhou Li, Tao HuangToken Compression Audio-Visual Reasoning
InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context
Mar 5, 2026Xin Teng, Canyu Zhang, Shaoyi Zheng +3Key-Value Context Length
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
Feb 8, 2026Haodong Li, Shaoteng Liu, Zhe Lin +1Autoregressive Video Diffusion Training-Free Inference Framework
Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation
Jun 13, 2025Mahmoud Amiri, Thomas BocklitzChunk Vast Chemical Space

Sep 17, 2026 · cs.AIJ/K move · Enter open · S save

Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure

Zofia Smoleń

Semantic cell annotation improves chunking interpretability for spreadsheets in LLM-driven RAG systems, aiding answer generation through enriched context rather than improved retrieval accuracy. We propose a novel framework of splitting any spreadsheet into interpretable chunks using cell role annotation. Our framework beats the state of the art, yet it faces a hard ceiling. Spreadsheets are fundamentally two-dimensional unstructured data with continuous relationships and infinite potential cell roles. Because classification models are restricted to finite, pre-defined classes, they cannot perfectly capture this structural nuance, even with human-level annotation. We show that addressing the spreadsheet-to-LLM bottleneck requires moving beyond discrete cell classification. Instead, the field must develop dimensionality-reduction techniques to directly flatten 2D unstructured spreadsheets into 1D unstructured text. Text chunks would be easier for downstream RAG to interpret and generate from.

Spreadsheets Chunk Hievi-Rag Retrieval-Augmented Generation Systems

Open paper Ask about it PDF