论文

[CL]《Enhancing Human-Like...

[CL]《Enhancing Human-Like Responses in Large Language Models》E Y Çalık, T R Akkuş (2025) 机器学习人工智能论文AI创造

2025-01-14 浏览详情

[LG] Neuro-Symbolic AI...

[LG] Neuro-Symbolic AI in 2024: A Systematic Review
机器学习人工智能论文AI创造营

2025-01-13 浏览详情

[LG]《Search-o1: Agentic...

[LG]《Search-o1: Agentic Search-Enhanced Large Reasoning Models》X Li, G Dong, J Jin, Y Zhang... [Renmin University of C

2025-01-13 浏览详情

[LG]《Key-value memory in the brain》...

[LG]《Key-value memory in the brain》S J. Gershman, I Fiete, K Irie [Harvard University & MIT] (2025) 机器学习人工智能论

2025-01-13 浏览详情

[LG]《Predicting the...

[LG]《Predicting the Performance of Black-box LLMs through Self-Queries》D Sam, M Finzi, J. Z Kolter [CMU] (2025) 机器学

2025-01-13 浏览详情

[LG]《Towards System...

[LG]《Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought》V Xiang, C Snell, K Gandhi,

2025-01-13 浏览详情

[LG]《Accelerated Diffusion...

[LG]《Accelerated Diffusion Models via Speculative Sampling》V D Bortoli, A Galashov, A Gretton, A Doucet [Google DeepMi

2025-01-13 浏览详情

看见手机就会使人降智看到一篇挺有...

看见手机就会使人降智

看到一篇挺有意思的心理学论文，对比了三种情况下以工作记忆和流动智力衡量的人的认知能力：看见手机，手机在兜

2025-01-12 浏览详情

[AS]《TangoFlux: Super...

[AS]《TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimiza

2025-01-11 浏览详情

[LG]《Edge of Stochastic...

[LG]《Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD》A Andreyev, P Beneventano [Princeton Unive

2025-01-08 浏览详情

[LG]《Unlearning-based...

[LG]《Unlearning-based Neural Interpretations》(2024) 人工智能机器学习论文AI创造营

2025-01-08 浏览详情

[AS]《Speech Recognition...

[AS]《Speech Recognition With LLMs Adapted to Disordered Speech Using Reinforcement Learning》C Nagpal, S Venugopalan, J

2025-01-07 浏览详情

[CL]《Dynamic Skill Adaptation...

[CL]《Dynamic Skill Adaptation for Large Language Models》J Chen, D Yang [Stanford University] (2024) 机器学习人工智能论

2025-01-07 浏览详情

[RO]《Data Scaling Laws...

[RO]《Data Scaling Laws in Imitation Learning for Robotic Manipulation》(2024) 人工智能机器学习论文AI创造营

2025-01-07 浏览详情

[LG]《Learning and aligning...

[LG]《Learning and aligning single-neuron invariance manifolds in visual cortex》(2024) AI创造营人工智能机器学习论文

2025-01-04 浏览详情

[LG] Introduction to...

[LG] Introduction to Graph Neural Networks: A Starting Point for Machine Learning Engineers
机器学习人工智能论文AI创造

2025-01-04 浏览详情

[LG]《MAP: Multi-Human-Value...

[LG]《MAP: Multi-Human-Value Alignment Palette》(2024) 人工智能机器学习论文AI创造营

2025-01-04 浏览详情

大城市住房供给限制造成的经济损失...

大城市住房供给限制造成的经济损失

一篇2019年AEJ: Macro论文估计了纽约、旧金山等美国大城市地方政府对住房供给做出的限制政策

2025-01-02 浏览详情

[IR]《Efficient Long...

[IR]《Efficient Long Context Language Model Retrieval with Compression》M Seo, J Baek, S Lee, S J Hwang [KAIST] (2024)

2025-01-01 浏览详情

[CL]《LLM2: Let Large...

[CL]《LLM2: Let Large Language Models Harness System 2 Reasoning》C Yang, C Shi, S Li, B Shui... [The Chinese University

2025-01-01 浏览详情

[LG]《Latent Bayesian...

[LG]《Latent Bayesian Optimization via Autoregressive Normalizing Flows》(2024) AI创造营人工智能机器学习论文

2024-12-31 浏览详情

[LG]《Convergence of...

[LG]《Convergence of Statistical Estimators via Mutual Information Bounds》E M Khribch, P Alquier [ESSEC Business School

2024-12-30 浏览详情

[CL]《State Space Models...

[CL]《State Space Models are Strong Text Rerankers》Z Xu, J Yan, A Gupta, V Srikumar [University of Utah] (2024) 机器学

2024-12-29 浏览详情

[LG]《HyperNet Fields:...

[LG]《HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories》E Hedlin

2024-12-29 浏览详情

[LG]《Rate of Model Collapse...

[LG]《Rate of Model Collapse in Recursive Training》A T Suresh, A Thangaraj, A N K Khandavally [Google Research & Indian

2024-12-28 浏览详情

[CV]《GIMS: Image Matching...

[CV]《GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network》X Song, Y Zou, Z Shi, Z

2024-12-28 浏览详情

[CL]《EscapeBench: Pushing...

[CL]《EscapeBench: Pushing Language Models to Think Outside the Box》C Qian, P Han, Q Luo, B He... [University of Illino

2024-12-27 浏览详情

[CL]《Deliberation in...

[CL]《Deliberation in Latent Space via Differentiable Cache Augmentation》L Liu, J Pfeiffer, J Wu, J Xie, A Szlam [Googl

2024-12-27 浏览详情

[LG]《SMOSE: Sparse Mixture...

[LG]《SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks》M V

2024-12-26 浏览详情

[CL]《Emergence of Abstractions:...

[CL]《Emergence of Abstractions: Concept Encoding and Decoding Mechanism for In-Context Learning in Transformers》S Han,

2024-12-26 浏览详情

[LG]《HashAttention:...

[LG]《HashAttention: Semantic Sparsity for Faster Inference》A Desai, S Yang, A Cuadron, A Klimovic... [UC Berkeley & E

2024-12-25 浏览详情

[LG]《Explainable Procedural...

[LG]《Explainable Procedural Mistake Detection》S Storks, I Bar-Yossef, Y Li, Z Zhang... [University of Michigan] (2024)

2024-12-24 浏览详情

[LG]《Cultural Evolution...

[LG]《Cultural Evolution of Cooperation among LLM Agents》A Vallinder, E Hughes [Google DeepMind] (2024) 机器学习人工智

2024-12-24 浏览详情

[LG]《Mastering Board...

[LG]《Mastering Board Games by External and Internal Planning with Language Models》J Schultz, J Adamek, M Jusup, M Lanc

2024-12-23 浏览详情

[CL]《How to Synthesize...

[CL]《How to Synthesize Text Data without Model Collapse?》X Zhu, D Cheng, H Li, K Zhang... [Shanghai Jiao Tong Universi

2024-12-23 浏览详情

[CL]《Smarter, Better,...

[CL]《Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finet

2024-12-23 浏览详情

[LG]《Analyzing (In)Abilities...

[LG]《Analyzing (In)Abilities of SAEs via Formal Languages》A Menon, M Shrivastava, D Krueger, E S Lubana [IIIT Hyderaba

2024-12-23 浏览详情

[CV]《MetaMorph: Multimodal...

[CV]《MetaMorph: Multimodal Understanding and Generation via Instruction Tuning》S Tong, D Fan, J Zhu, Y Xiong... [Meta]

2024-12-23 浏览详情

[LG]《No Free Lunch From...

[LG]《No Free Lunch From Random Feature Ensembles》B S. Ruben, W L. Tong, H T Chaudhry, C Pehlevan [Harvard University]

2024-12-22 浏览详情

[CV]《[MASK] is All You Need》...

[CV]《[MASK] is All You Need》V T Hu, B Ommer [LMU Munich] (2024) 机器学习人工智能论文 AI创造营

2024-12-22 浏览详情

[LG]《Entropy-Regularized...

[LG]《Entropy-Regularized Process Reward Model》H Zhang, P Wang, S Diao, Y Lin… [University of Illinois Urbana-Champaig

2024-12-22 浏览详情

[IR]《Semantic Retrieval at Walmart》...

[IR]《Semantic Retrieval at Walmart》A Magnani, F Liu, S Chaidaroon, S Yadav... [Walmart Global Technology] (2024) 机器

2024-12-22 浏览详情

[CL]《Forest-of-Thought:...

[CL]《Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning》Z Bi, K Han, C Liu, Y Tang... [Huawei No

2024-12-21 浏览详情

[LG]《Discover Physical...

[LG]《Discover Physical Concepts and Equations with Machine Learning》B Li, Y Gu, S Wu [Shanghai University & Ludwig-Max

2024-12-20 浏览详情

[LG]《Neural general...

[LG]《Neural general circulation models optimized to predict satellite-based precipitation observations》J Yuval, I Lang

2024-12-20 浏览详情

[CL]《Understanding Knowledge...

[CL]《Understanding Knowledge Hijack Mechanism in In-context Learning through Associative Memory》S Wang, I Sato [The Un

2024-12-19 浏览详情

[LG] Superhuman performance...

[LG] Superhuman performance of a large language model on the reasoning tasks of a physician
机器学习人工智能论文#AI创

2024-12-19 浏览详情

[CL] The Open Source...

[CL] The Open Source Advantage in Large Language Models (LLMs)
机器学习人工智能论文#AI创造营#
本文比较分析了开源和闭

2024-12-19 浏览详情

[CL] Reinforcement Learning...

[CL] Reinforcement Learning Enhanced LLMs: A Survey
机器学习人工智能论文#AI创造营#
本文对利用强化学习增强大型语言模型

2024-12-19 浏览详情

[LG]《How to Merge Your...

[LG]《How to Merge Your Multimodal Models Over Time?》S Dziadzio, V Udandarao, K Roth, A Prabhu... [University of T ̈ub

2024-12-19 浏览详情

[RO]《RLDG: Robotic Generalist...

[RO]《RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning》C Xu, Q Li, J Luo, S Levine [UC Berkeley]

2024-12-18 浏览详情

[LG]《Efficient Online...

[LG]《Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data》Z Zhou, A Peng, Q Li, S Levine..

2024-12-16 浏览详情

[LG]《Sinkhorn Algorithm...

[LG]《Sinkhorn Algorithm for Sequentially Composed Optimal Transports》K Watanabe, N Isobe [National Institute of Inform

2024-12-16 浏览详情

网上色情对结婚率的影响一篇2016年...

网上色情对结婚率的影响

一篇2016年EEJ论文研究了一个神奇的话题：越来越多的年轻男性在网上看小电影是美国结婚率下降的原因吗？作

2024-12-16 浏览详情

[LG]《Statistical Downscaling...

[LG]《Statistical Downscaling via High-Dimensional Distribution Matching with Generative Models》Z Y Wan, I Lopez-Gomez,

2024-12-15 浏览详情

[CL]《Advancing Single-...

[CL]《Advancing Single- and Multi-task Text Classification through Large Language Model Fine-tuning》H Zhao, Q P. Chen,

2024-12-14 浏览详情

[LG]《APOLLO: SGD-like...

[LG]《APOLLO: SGD-like Memory, AdamW-level Performance》H Zhu, Z Zhang, W Cong, X Liu... [The University of Texas at Aus

2024-12-13 浏览详情

[CV]《Normalizing Flows...

[CV]《Normalizing Flows are Capable Generative Models》S Zhai, R Zhang, P Nakkiran, D Berthelot... [Apple] (2024) 机器学

2024-12-13 浏览详情

[CL]《Mixture of Hidden-Dimensions...

[CL]《Mixture of Hidden-Dimensions Transformer》Y Chen, J Shang, Z Zhang, J Sheng... [Chinese Academy of Sciences] (2024

2024-12-13 浏览详情

[CL]《Best-of-N Jailbreaking》...

[CL]《Best-of-N Jailbreaking》J Hughes, S Price, A Lynch, R Schaeffer... [Speechmatics & MATS] (2024) 机器学习人工智能论

2024-12-13 浏览详情

[LG]《Revisiting the...

[LG]《Revisiting the Initial Steps in Adaptive Gradient Descent Optimization》A Abuduweili, C Liu [CMU] (2024) 机器学习

2024-12-13 浏览详情

[CL]《ProcessBench: Identifying...

[CL]《ProcessBench: Identifying Process Errors in Mathematical Reasoning》C Zheng, Z Zhang, B Zhang, R Lin... [Alibaba I

2024-12-12 浏览详情

[LG]《Flex Attention:...

[LG]《Flex Attention: A Programming Model for Generating Optimized Attention Kernels》J Dong, B Feng, D Guessous, Y Lian

2024-12-12 浏览详情

[CL]《ALMA: Alignment...

[CL]《ALMA: Alignment with Minimal Annotation》M Yasunaga, L Shamis, C Zhou, A Cohen… [Meta] (2024) 机器学习人工智能论

2024-12-12 浏览详情

[LG]《Weak-to-Strong...

[LG]《Weak-to-Strong Generalization Through the Data-Centric Lens》C Shin, J Cooper, F Sala [University of Wisconsin-Mad

2024-12-10 浏览详情

[LG]《FlashAttention...

[LG]《FlashAttention on a Napkin: A Diagrammatic Approach to Deep Learning IO-Awareness》V Abbott, G Zardini [University

2024-12-09 浏览详情

[CL]《KV Shifting Attention...

[CL]《KV Shifting Attention Enhances Language Modeling》M Xu, W Cheng, B Wang, W Chen [Baichuan Inc.] (2024) 机器学习人

2024-12-09 浏览详情

[LG]《The Cost of Consistency:...

[LG]《The Cost of Consistency: Submodular Maximization with Constant Recourse》P Dütting, F Fusco, S Lattanzi, A Norouz

2024-12-08 浏览详情

[LG]《Theoretical limitations...

[LG]《Theoretical limitations of multi-layer Transformer》L Chen, B Peng, H Wu [UC Berkeley] (2024) 机器学习人工智能论文

2024-12-07 浏览详情

[LG]《Self-Improvement...

[LG]《Self-Improvement in Language Models: The Sharpening Mechanism》A Huang, A Block, D J. Foster, D Rohatgi... [Micros

2024-12-07 浏览详情

[CV]《Enhancing Deep...

[CV]《Enhancing Deep Learning Model Robustness through Metamorphic Re-Training》S Togru, Y S Mostafa, K Lotfy [Technical

2024-12-06 浏览详情

[LG]《Learning by Self-Explaining》...

[LG]《Learning by Self-Explaining》W Stammer, F Friedrich, D Steinmann, M Brack... [TU Darmstadt] (2024) 机器学习人工智

2024-12-05 浏览详情

[LG]《Safety Alignment...

[LG]《Safety Alignment Should be Made More Than Just a Few Tokens Deep》人工智能机器学习论文

2024-12-05 浏览详情

[LG]《Anytime Acceleration...

[LG]《Anytime Acceleration of Gradient Descent》Z Zhang, J D. Lee, S S. Du, Y Chen [U. Washington & Princeton] (2024) 机

2024-12-04 浏览详情

[CV]《SAMURAI: Adapting...

[CV]《SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory》C Yang, H Huang,

2024-12-04 浏览详情

[CL]《LLMs Do Not Think...

[CL]《LLMs Do Not Think Step-by-step In Implicit Reasoning》Y Yu [Tsinghua University] (2024) 机器学习人工智能论文

2024-12-04 浏览详情

[CL]《Reverse Thinking...

[CL]《Reverse Thinking Makes LLMs Stronger Reasoners》J C Chen, Z Wang, H Palangi, R Han… [UNC Chapel Hill & Google Clo

2024-12-04 浏览详情

[LG]《nGPT: Normalized...

[LG]《nGPT: Normalized Transformer with Representation Learning on the Hypersphere》I Loshchilov, C Hsieh, S Sun, B Gins

2024-12-04 浏览详情

[LG]《JetFormer: An Autoregressive...

[LG]《JetFormer: An Autoregressive Generative Model of Raw Images and Text》M Tschannen, A S Pinto, A Kolesnikov [Google

2024-12-04 浏览详情

[LG]《A Flexible Defense...

[LG]《A Flexible Defense Against the Winner's Curse》T Zrnic, W Fithian [Stanford University & UC Berkeley] (2024) 机器

2024-12-04 浏览详情

[CL]《Sneaking Syntax...

[CL]《Sneaking Syntax into Transformer Language Models with Tree Regularization》A Nandi, C D. Manning, S Murty [Stanfor

2024-12-04 浏览详情

[CL]《The Extractive-Abstractive...

[CL]《The Extractive-Abstractive Spectrum: Uncovering Verifiability Trade-offs in LLM Generations》T Worledge, T Hashimo

2024-12-04 浏览详情

[LG]《Spread Preference...

[LG]《Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment》人工智能机器学习论文

2024-12-04 浏览详情

[LG]《NeuroAI for AI Safety》...

[LG]《NeuroAI for AI Safety》P Mineault, N Zanichelli, J Z Peng, A Arkhipov... [Amaranth Foundation] (2024) 机器学习人工

2024-12-04 浏览详情

[LG]《HiBO: Hierarchical...

[LG]《HiBO: Hierarchical Bayesian Optimization via Adaptive Search Space Partitioning》(2024) 人工智能机器学习论文

2024-12-04 浏览详情

[LG]《LoRA Done RITE:...

[LG]《LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization》人工智能机器学习论文

2024-12-04 浏览详情

[IR]《Drowning in Documents:...

[IR]《Drowning in Documents: Consequences of Scaling Reranker Inference》M Jacob, E Lindgren, M Zaharia, M Carbin... [Da

2024-12-02 浏览详情

今日推介(第1603期)：长序列的高效LLM推理...

今日推介(第1603期)：长序列的高效LLM推理、不完美验证器LLM重采样的局限性、任意时刻加速梯度下降、基于语言游戏的无界苏格拉底学

2024-12-02 浏览详情

今日推介(第1604期)：AI生成内容的水印...

今日推介(第1604期)：AI生成内容的水印、紧凑高效的人机对话安全审核模型、对抗赢家诅咒问题的缩放校正方法、用动态词元化方法改造

2024-12-01 浏览详情

[LG]《Llama Guard 3-1B-INT4:...

[LG]《Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations》I Fedorov, K Plawiak, L Wu, T E

2024-12-01 浏览详情

[LG]《Retrofitting (Large)...

[LG]《Retrofitting (Large) Language Models with Dynamic Tokenization》D Feher, B Minixhofer, I Vulić [University of Cam

2024-12-01 浏览详情

[LG]《Cautious Optimizers:...

[LG]《Cautious Optimizers: Improving Training with One Line of Code》K Liang, L Chen, B Liu, Q Liu (2024) 机器学习人工智

2024-12-01 浏览详情

[CL]《Exploring Facets...

[CL]《Exploring Facets of Language Generation in the Limit》M Charikar, C Pabbaraju [Stanford University] (2024) 机器学

2024-11-30 浏览详情

[CL]《Self-Generated...

[CL]《Self-Generated Critiques Boost Reward Modeling for Language Models》Y Yu, Z Chen, A Zhang, L Tan... [Meta] (2024)

2024-11-29 浏览详情

[CL]《Bi-Mamba: Towards...

[CL]《Bi-Mamba: Towards Accurate 1-Bit State Space Models》S Tang, L Ma, H Li, M Sun... [Mohamed bin Zayed University of

2024-11-29 浏览详情

[CL]《Do Large Language...

[CL]《Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?》S Yang, N Kassner, E Gr

2024-11-29 浏览详情

[CL]《From Jack of All...

[CL]《From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set》M Finkelstein, D Deutsc

2024-11-29 浏览详情

[CL]《Arithmetic Without...

[CL]《Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics》Y Nikankin, A Reusch, A Muelle

2024-11-29 浏览详情

[RO]《Instant Policy:...

[RO]《Instant Policy: In-Context Imitation Learning via Graph Diffusion》V Vosylius, E Johns [Imperial College London] (

2024-11-28 浏览详情

[LG]《Are Large Language...

[LG]《Are Large Language Models Memorizing Bug Benchmarks?》D Ramos, C Mamede, K Jain, P Canelas... [CMU] (2024) 机器学

2024-11-28 浏览详情