16k
1개 벤치마크 · 논문 146편 · 이 태스크의 논문 보기 →
Benchmarks
ConceptNet
Most implemented
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Long Range Arena: A Benchmark for Efficient Transformers
Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
Long-form factuality in large language models
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
Papers
UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation
Unified multimodal large language models (MLLMs) have shown promise in jointly advancing multimodal understanding and generation, with visual codebooks discretizing images into tokens for autoregressive modeling. Existin…
16kMSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling
Scene text retrieval has made significant progress with the assistance of accurate text localization. However, existing approaches typically require costly bounding box annotations for training. Besides, they mostly adop…
16kRetrievalText RetrievalHow Far Are We from Optimal Reasoning Efficiency?
Large Reasoning Models (LRMs) demonstrate remarkable problem-solving capabilities through extended Chain-of-Thought (CoT) reasoning but often produce excessively verbose and redundant reasoning traces. This inefficiency …
16kBenchmarkingNumerical IntegrationFlashDMoE: Fast Distributed MoE in a Single Kernel
The computational sparsity of Mixture-of-Experts (MoE) models enables sub-linear growth in compute cost as model size increases, thus offering a scalable path to training massive neural networks. However, existing implem…
16kCPUGPUMixture-of-Experts+1FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian
The development of speech foundation models (SFMs) like Whisper and SeamlessM4T has significantly advanced the field of speech processing. However, their closed nature--with inaccessible training data and code--poses maj…
16kSpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences
Speculative decoding is a widely adopted technique for accelerating inference in large language models (LLMs), but its performance degrades on long inputs due to increased attention cost and reduced draft accuracy. We in…
16kLong-Context Understanding