{"total":90,"rows":[{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554,"area":null},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2501.18795","title":"Rope to Nope and Back Again: A New Hybrid Attention Strategy","created":"2025-01-30","cited_by_count":47,"area":null},{"id":"2509.06888","title":"mmBERT: A Modern Multilingual Encoder with Annealed Language Learning","created":"2025-09-08","cited_by_count":45,"area":null},{"id":"2507.11412","title":"Seq vs Seq: An Open Suite of Paired Encoders and Decoders","created":"2025-07-15","cited_by_count":38,"area":null},{"id":"2504.04635","title":"Steering off Course: Reliability Challenges in Steering Language Models","created":"2025-04-06","cited_by_count":34,"area":null},{"id":"2503.05500","title":"EuroBERT: Scaling Multilingual Encoders for European Languages","created":"2025-03-07","cited_by_count":31,"area":null},{"id":"2501.05414","title":"LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2501.04961","title":"Demystifying Domain-adaptive Post-training for Financial LLMs","created":"2025-01-09","cited_by_count":24,"area":null},{"id":"2502.20082","title":"LongRoPE2: Near-Lossless LLM Context Window Scaling","created":"2025-02-27","cited_by_count":24,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2501.12766","title":"NExtLong: Toward Effective Long-Context Training without Long Documents","created":"2025-01-22","cited_by_count":20,"area":null},{"id":"2503.01996","title":"One ruler to measure them all: Benchmarking multilingual long-context language models","created":"2025-03-03","cited_by_count":19,"area":null},{"id":"2504.08719","title":"SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling","created":"2025-04-11","cited_by_count":19,"area":null},{"id":"2411.13476","title":"When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training","created":"2024-11-20","cited_by_count":15,"area":null},{"id":"2502.07365","title":"LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2503.09202","title":"Token Weighting for Long-Range Language Modeling","created":"2025-03-12","cited_by_count":14,"area":null},{"id":"2510.10481","title":"UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models","created":"2025-10-12","cited_by_count":13,"area":null},{"id":"2512.12087","title":"BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding","created":"2025-12-12","cited_by_count":13,"area":null},{"id":"2511.21016","title":"Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression","created":"2025-11-26","cited_by_count":11,"area":null},{"id":"2410.23463","title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2502.21231","title":"ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12,000 GPUs","created":"2025-02-28","cited_by_count":10,"area":null},{"id":"2506.17121","title":"Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?","created":"2025-06-20","cited_by_count":10,"area":null},{"id":"2502.16684","title":"WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2502.16860","title":"LongAttn: Selecting Long-context Training Data via Token-level Attention","created":"2025-02-24","cited_by_count":9,"area":null},{"id":"2506.11440","title":"AbsenceBench: Language Models Can't Tell What's Missing","created":"2025-06-13","cited_by_count":9,"area":null},{"id":"2505.19959","title":"MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2605.15514","title":"RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","cited_by_count":7,"area":null},{"id":"2503.15450","title":"SkyLadder: Better and Faster Pretraining via Context Window Scheduling","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2504.21463","title":"RWKV-X: A Linear Complexity Hybrid Language Model","created":"2025-04-30","cited_by_count":6,"area":null},{"id":"2505.17134","title":"LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2509.21271","title":"SuperOffload: Unleashing the Power of Large-Scale LLM Training on Superchips","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2505.13136","title":"New Encoders for German Trained from Scratch: Comparing ModernGBERT with Converted LLM2Vec Models","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2505.17083","title":"Scale-invariant Attention","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2505.19293","title":"100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2510.05862","title":"Revisiting Long-context Modeling from Context Denoising Perspective","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2512.19097","title":"DIVER-1: Scaling Intracranial EEG Foundation Models for Transferable Representations","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2601.09066","title":"Mi:dm 2.0 Korea-centric Bilingual Language Models","created":"2026-01-14","cited_by_count":5,"area":null},{"id":"2606.04511","title":"SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference","created":"2026-06-03","cited_by_count":5,"area":null},{"id":"2504.15431","title":"Trillion 7B Technical Report","created":"2025-04-21","cited_by_count":4,"area":null},{"id":"2512.03494","title":"A Preliminary Study on the Promises and Challenges of Native Top-$k$ Sparse Attention","created":"2025-12-03","cited_by_count":3,"area":null},{"id":"2603.11352","title":"TimeSqueeze: Dynamic Patching for Efficient Time Series Forecasting","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2603.17484","title":"Learning When to Attend: Conditional Memory Access for Long-Context LLMs","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2604.15180","title":"AdaSplash-2: Faster Differentiable Sparse Attention","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2609.02986","title":"Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design","created":"2026-09-02","cited_by_count":3,"area":null},{"id":"2504.03931","title":"NAACL2025 Tutorial: Adaptation of Large Language Models","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2507.09506","title":"Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2507.19786","title":"Flora: Effortless Context Construction to Arbitrary Length and Scale","created":"2025-07-26","cited_by_count":2,"area":null},{"id":"2510.24345","title":"LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2602.05258","title":"CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2602.09075","title":"Learning to Remember, Learn, and Forget in Attention-Based Models","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2602.22175","title":"DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2604.22575","title":"SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2608.01672","title":"Learning What to Remember: Test-Time Training via Context Distillation","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2505.06496","title":"xGen-small Technical Report","created":"2025-05-10","cited_by_count":1,"area":null},{"id":"2509.18762","title":"When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2509.22630","title":"StateX: Enhancing RNN Recall via Post-training State Expansion","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.18830","title":"MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2603.18446","title":"UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.02650","title":"Revealing the Learning Dynamics of Long-Context Continual Pre-training","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2605.09877","title":"Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2608.12218","title":"Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2410.11457","title":"LR-SQL: A Supervised Fine-Tuning Method for Text2SQL Tasks under Low-Resource Scenarios","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2410.12292","title":"How much do contextualized representations encode long-range context?","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2507.19419","title":"TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2510.18121","title":"Efficient Long-context Language Model Training by Core Attention Disaggregation","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2601.13734","title":"Towards robust long-context understanding of large language model via active recap learning","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.08237","title":"Document Reconstruction Unlocks Scalable Long-Context RLVR","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.15005","title":"Pretraining and Benchmarking Modern Encoders for Latvian","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.02371","title":"Internalized Reasoning for Long-Context Visual Document Understanding","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.24715","title":"Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.26902","title":"ICICLE: Expanding Retrieval with In-Context Documents","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.03078","title":"G^2C-MT: Graph-Guided Context Selection for Document-Level Machine Translation","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.21890","title":"Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.11614","title":"Extending LLM Context via Associative Recurrent Memory","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.01034","title":"Opt.Gear Technical Report","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.10296","title":"Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.17616","title":"MoNe: Modular Neural Memory for Efficient Long Context Inference","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.19920","title":"Learning how to Forget: Fine-tuning for Long-Context Sparse Attention","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.26828","title":"Bridging LLM Serving and CXL-SSDs with Chunk-Aware KV Cache Management","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.27964","title":"Linear RNN Scaling Laws: When Longer Sequences Beat More Sequences","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.29245","title":"No More Free Lunch: Corpus Task Complexity Matters as Corpora Grow","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.32759","title":"The Extender: A Log-Structured Transformer","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34556","title":"RoPE is Dead, Long Live RoPE: Towards Scalable Data-aware Positional Encodings","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38109","title":"How Local Mixing Encodes Relative Position in Global NoPE Attention","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04518","title":"Length Generalization Needs Proper Regularization","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.06963","title":"WavePrune: One period is often enough for RoPE","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.13735","title":"Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15028","title":"UltraBERT: Beyond the Limit of BERT Pre-Training","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}