conftrace_

long context

121 papers

Explore in graph

Co-occurring keywords

large language model (13587) language model (4599) question answering (2963) attention mechanism (4001) context window (73) retrieval-augmented generation (1592) kv cache (74) efficient computing (781) information retrieval (1514) context length (48)

Papers

A2ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization ACL 2025
LongReward: Improving Long-context Large Language Models with AI Feedback ACL 2025
Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios NAACL 2025
Re3Syn: A Dependency-Based Data Synthesis Framework for Long-Context Post-training ACL 2025
Towards Long Context Hallucination Detection NAACL 2025
Long Context Tuning for Video Generation ICCV 2025
Search-in-Context: Efficient Multi-Hop QA over Long Contexts via Monte Carlo Tree Search with Dynamic KV Retrieval ACL 2025
MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference NAACL 2025
Towards Infinite-Long Prefix in Transformer EMNLP 2025
Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning EMNLP 2025
Unstructured Evidence Attribution for Long Context Query Focused Summarization EMNLP 2025
Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps EMNLP 2025
DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs EMNLP 2025
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval EMNLP 2025
From General Reward to Targeted Reward: Improving Open-ended Long-context Generation Models EMNLP 2025
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection EMNLP 2025
PRISM: Efficient Long-Range Reasoning With Short-Context LLMs EMNLP 2025
OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Question Answering EMNLP 2025
Long-context Reference-based MT Quality Estimation EMNLP 2025
One-Minute Video Generation with Test-Time Training CVPR 2025
Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts EMNLP 2025
DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming AAAI 2025
Structured Packing in LLM Training Improves Long Context Utilization AAAI 2025
BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack NIPS 2024
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding NIPS 2024