{"list":"other","total":99,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832},{"id":"2412.06769","title":"Training Large Language Models to Reason in a Continuous Latent Space","created":"2024-12-09","cited_by_count":797},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"2401.09670","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","created":"2024-01-18","cited_by_count":617},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"2401.18079","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","created":"2024-01-31","cited_by_count":591},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"2310.01801","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","created":"2023-10-03","cited_by_count":474},{"id":"2305.17118","title":"Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time","created":"2023-05-26","cited_by_count":439},{"id":"2502.05171","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","created":"2025-02-07","cited_by_count":415},{"id":"2201.05596","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","created":"2022-01-14","cited_by_count":404},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310},{"id":"2404.16710","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","created":"2024-04-25","cited_by_count":307},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301},{"id":"2310.02226","title":"Think before you speak: Training Language Models With Pause Tokens","created":"2023-10-03","cited_by_count":264},{"id":"2404.02258","title":"Mixture-of-Depths: Dynamically allocating compute in transformer-based language models","created":"2024-04-02","cited_by_count":258},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252},{"id":"2004.04037","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","created":"2020-04-08","cited_by_count":251},{"id":"2502.17416","title":"Reasoning with Latent Thoughts: On the Power of Looped Transformers","created":"2025-02-24","cited_by_count":240},{"id":"2301.13196","title":"Looped Transformers as Programmable Computers","created":"2023-01-30","cited_by_count":237},{"id":"1910.10073","title":"Depth-Adaptive Transformer","created":"2019-10-22","cited_by_count":236},{"id":"2502.21074","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","created":"2025-02-28","cited_by_count":225},{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219},{"id":"2408.15664","title":"Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts","created":"2024-08-28","cited_by_count":205},{"id":"2412.13171","title":"Compressed Chain of Thought: Efficient Reasoning Through Dense Representations","created":"2024-12-17","cited_by_count":201},{"id":"2404.15758","title":"Let's Think Dot by Dot: Hidden Computation in Transformer Language Models","created":"2024-04-24","cited_by_count":191},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186},{"id":"2312.15166","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","created":"2023-12-23","cited_by_count":172},{"id":"1511.06297","title":"Conditional Computation in Neural Networks for faster models","created":"2015-11-19","cited_by_count":167},{"id":"2302.07863","title":"Speculative Decoding with Big Little Decoder","created":"2023-02-15","cited_by_count":164},{"id":"2403.05527","title":"GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM","created":"2024-03-08","cited_by_count":158},{"id":"2311.12424","title":"Looped Transformers are Better at Learning Learning Algorithms","created":"2023-11-21","cited_by_count":149},{"id":"2405.12532","title":"PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference","created":"2024-05-21","cited_by_count":147},{"id":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144},{"id":"2405.12981","title":"Reducing Transformer Key-Value Cache Size with Cross-Layer Attention","created":"2024-05-21","cited_by_count":131},{"id":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122},{"id":"2403.09636","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","created":"2024-03-14","cited_by_count":116},{"id":"2204.08396","title":"StableMoE: Stable Routing Strategy for Mixture of Experts","created":"2022-04-18","cited_by_count":100},{"id":"2409.15647","title":"Looped Transformers for Length Generalization","created":"2024-09-24","cited_by_count":99},{"id":"2505.07686","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","created":"2025-05-12","cited_by_count":87},{"id":"2104.06022","title":"Lessons on Parameter Sharing across Layers in Transformers","created":"2021-04-13","cited_by_count":85},{"id":"2310.05424","title":"Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding","created":"2023-10-09","cited_by_count":80},{"id":"1802.08770","title":"A Walk with SGD","created":"2018-02-24","cited_by_count":78},{"id":"2410.20672","title":"Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA","created":"2024-10-28","cited_by_count":78},{"id":"2405.03917","title":"KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization","created":"2024-05-07","cited_by_count":76},{"id":"1509.08971","title":"Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition","created":"2015-09-29","cited_by_count":67},{"id":"2410.08292","title":"Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?","created":"2024-10-10","cited_by_count":65},{"id":"2405.10637","title":"Layer-Condensed KV Cache for Efficient Inference of Large Language Models","created":"2024-05-17","cited_by_count":59},{"id":"2502.13842","title":"Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking","created":"2025-02-19","cited_by_count":57},{"id":"2406.03372","title":"Training of Physical Neural Networks","created":"2024-06-05","cited_by_count":49},{"id":"2310.12072","title":"SPEED: Speculative Pipelined Execution for Efficient Decoding","created":"2023-10-18","cited_by_count":47},{"id":"2505.20674","title":"PonderLM: Pretraining Language Models to Ponder in Continuous Space","created":"2025-05-27","cited_by_count":44},{"id":"2502.08524","title":"LLM Pretraining with Continuous Concepts","created":"2025-02-12","cited_by_count":36},{"id":"2310.07096","title":"Sparse Universal Transformer","created":"2023-10-11","cited_by_count":32},{"id":"2505.13949","title":"FlashThink: An Early Exit Method For Efficient Reasoning","created":"2025-05-20","cited_by_count":28},{"id":"2412.17747","title":"Deliberation in Latent Space via Differentiable Cache Augmentation","created":"2024-12-23","cited_by_count":26},{"id":"2502.01567","title":"Latent Thought Models with Variational Bayes Inference-Time Computation","created":"2025-02-03","cited_by_count":25},{"id":"2311.15436","title":"Learning to Skip for Language Modeling","created":"2023-11-26","cited_by_count":19},{"id":"2412.04449","title":"p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay","created":"2024-12-05","cited_by_count":16},{"id":"2410.13859","title":"$\\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models","created":"2024-10-17","cited_by_count":14},{"id":"2409.14199","title":"Loop Neural Networks for Parameter Sharing","created":"2024-09-21","cited_by_count":11},{"id":"2309.06589","title":"Do Generative Large Language Models need billions of parameters?","created":"2023-09-12","cited_by_count":8},{"id":"2412.20875","title":"Attention Is All You Need For Mixture-of-Depths Routing","created":"2024-12-30","cited_by_count":7},{"id":"2507.08567","title":"AbbIE: Autoregressive Block-Based Iterative Encoder for Efficient Sequence Modeling","created":"2025-07-11","cited_by_count":7},{"id":"2412.19325","title":"Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones","created":"2024-12-26","cited_by_count":4}],"next_cursor":null}