Skip to yearly menu bar Skip to main content


Workshop Thu, Jul 9, 2026 • 4:00 PM – 1:00 AM PDT ROOM 318

Foundations of Deep Generative Models: Understanding Memorization, Generalization, and Reasoning

Wei Huang ⋅ Qing Qu ⋅ Renyuan Xu ⋅ Valentin De Bortoli ⋅ Molei Tao ⋅ John Vastola ⋅ Peng Wang ⋅ Xiao Li ⋅ GEORGIOS PAPAIOANNOU ⋅ Beatrice Achilli
Project Page [ OpenReview] 

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
4:00 PM
Qing Qu
5:10 PM
Poster & Break
7:45 PM
Lunch Break
9:00 PM
Mengdi Wang
10:00 PM
Poster & Break
12:00 AM
Panel Discussion
12:50 AM
Awards & Closing
Interdomain Attention: Beyond Token-Level Key-Value Memory
Naoki Kiyohara ⋅ Harrison B Zhu ⋅ Riccardo El Hassanin ⋅ Zhuo Sun ⋅ Wenlong Chen ⋅ Samir Bhatt ⋅ Yingzhen Li
Interdomain Attention: Beyond Token-Level Key-Value Memory
Naoki Kiyohara ⋅ Harrison B Zhu ⋅ Riccardo El Hassanin ⋅ Zhuo Sun ⋅ Wenlong Chen ⋅ Samir Bhatt ⋅ Yingzhen Li
Time-Correlated Video Bridge Matching
Viacheslav Vasilev ⋅ Arseny Ivanov ⋅ Nikita Gushchin ⋅ Maria Kovaleva ⋅ Aleksandr Korotin
Time-Correlated Video Bridge Matching
Viacheslav Vasilev ⋅ Arseny Ivanov ⋅ Nikita Gushchin ⋅ Maria Kovaleva ⋅ Aleksandr Korotin
LLM Generation Novelty Through the Lens of Semantic Similarity
Philipp Davydov ⋅ Ameya Pandurang Prabhu ⋅ Matthias Bethge ⋅ Elisa Nguyen ⋅ Seong Joon Oh
LLM Generation Novelty Through the Lens of Semantic Similarity
Philipp Davydov ⋅ Ameya Pandurang Prabhu ⋅ Matthias Bethge ⋅ Elisa Nguyen ⋅ Seong Joon Oh
Reinforcement Learning with Promising Tokens for Large Language Models
Jing-Cheng Pang ⋅ Liang Lu ⋅ Xian Tang ⋅ KUN JIANG ⋅ Sijie Wu ⋅ Kai Zhang ⋅ Xubin Li
Reinforcement Learning with Promising Tokens for Large Language Models
Jing-Cheng Pang ⋅ Liang Lu ⋅ Xian Tang ⋅ KUN JIANG ⋅ Sijie Wu ⋅ Kai Zhang ⋅ Xubin Li
SALSA: State Augmentation via Learned Selective Attention
Joel Manu ⋅ Frederick Hoffman ⋅ Krithik Ramesh
SALSA: State Augmentation via Learned Selective Attention
Joel Manu ⋅ Frederick Hoffman ⋅ Krithik Ramesh
DPRM: A Plug-in Token-Ordering Module for Diffusion Language Models
Dake Bu ⋅ Wei Huang ⋅ Andi Han ⋅ Hau-San Wong ⋅ Qingfu Zhang ⋅ Taiji Suzuki ⋅ Atsushi Nitanda
DPRM: A Plug-in Token-Ordering Module for Diffusion Language Models
Dake Bu ⋅ Wei Huang ⋅ Andi Han ⋅ Hau-San Wong ⋅ Qingfu Zhang ⋅ Taiji Suzuki ⋅ Atsushi Nitanda
Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
Lunjun Zhang ⋅ Ryan Chen ⋅ Bradly Stadie
Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
Lunjun Zhang ⋅ Ryan Chen ⋅ Bradly Stadie
Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
Lingxiao Li ⋅ Haobo Zhang ⋅ Bin Chen ⋅ Jiayu Zhou
Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
Lingxiao Li ⋅ Haobo Zhang ⋅ Bin Chen ⋅ Jiayu Zhou
Reasoning Across Space: Tiny Recursive Models for Spatial Omics
Dhruva Abhijit Rajwade ⋅ Marianna Rapsomaniki
Reasoning Across Space: Tiny Recursive Models for Spatial Omics
Dhruva Abhijit Rajwade ⋅ Marianna Rapsomaniki
Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics
Benjamin Sterling ⋅ Monica Bugallo ⋅ Tom Tirer
Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics
Benjamin Sterling ⋅ Monica Bugallo ⋅ Tom Tirer
Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs
Hongkang Li ⋅ Hancheng Min ⋅ Rene Vidal
Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs
Hongkang Li ⋅ Hancheng Min ⋅ Rene Vidal
Temporal Task Diversity: Inductive Biases Under Non-Stationarity in Synthetic Sequence Modelling
Afiq A Aswadi ⋅ Oliver Britton ⋅ Ross Baker ⋅ Matthew Farrugia-Roberts
Temporal Task Diversity: Inductive Biases Under Non-Stationarity in Synthetic Sequence Modelling
Afiq A Aswadi ⋅ Oliver Britton ⋅ Ross Baker ⋅ Matthew Farrugia-Roberts
Velocity Adaptation for Flow-Matching Models
Sai Praneeth ⋅ Gouri Shanker ⋅ Harshit Dubey ⋅ Chandra Sekhar Seelamantula
Velocity Adaptation for Flow-Matching Models
Sai Praneeth ⋅ Gouri Shanker ⋅ Harshit Dubey ⋅ Chandra Sekhar Seelamantula
Frontier Language Models Struggle to Copy: Text Can Be Better Viewed in 2D
Haodong Wen ⋅ Yiran Zhang ⋅ Yingfa Chen ⋅ Kaifeng Lyu
Frontier Language Models Struggle to Copy: Text Can Be Better Viewed in 2D
Haodong Wen ⋅ Yiran Zhang ⋅ Yingfa Chen ⋅ Kaifeng Lyu
Revisiting Spectral Representations in Generative Diffusion Models
Yuehao Wang ⋅ Peihao Wang ⋅ Hanwen Jiang ⋅ Ziyi Yang ⋅ Qixing Huang ⋅ Zhangyang “Atlas” Wang
Revisiting Spectral Representations in Generative Diffusion Models
Yuehao Wang ⋅ Peihao Wang ⋅ Hanwen Jiang ⋅ Ziyi Yang ⋅ Qixing Huang ⋅ Zhangyang “Atlas” Wang
Context Over Content: Exposing Evaluation Faking in Automated Judges
Manan Gupta ⋅ Inderjeet J Nair ⋅ Lu Wang ⋅ Dhruv Kumar
Context Over Content: Exposing Evaluation Faking in Automated Judges
Manan Gupta ⋅ Inderjeet J Nair ⋅ Lu Wang ⋅ Dhruv Kumar
Enhancing Knowledge Injection with Surrounding Backgrounds in Continual Training LLMs
Zichen TANG ⋅ Zhenheng Tang ⋅ Yifan Hou ⋅ Peijie Dong ⋅ Xiang Liu ⋅ Shaohuai Shi ⋅ Xiaowen Chu ⋅ Bo Li
Enhancing Knowledge Injection with Surrounding Backgrounds in Continual Training LLMs
Zichen TANG ⋅ Zhenheng Tang ⋅ Yifan Hou ⋅ Peijie Dong ⋅ Xiang Liu ⋅ Shaohuai Shi ⋅ Xiaowen Chu ⋅ Bo Li
ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?
Haonan Han ⋅ Jiancheng Huang ⋅ Xiaopeng Sun ⋅ Jun-Yan He ⋅ Rui Yang ⋅ Jie Hu ⋅ Xiaojiang Peng ⋅ Lin Ma ⋅ Xiaoming Wei ⋅ Xiu Li
ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?
Haonan Han ⋅ Jiancheng Huang ⋅ Xiaopeng Sun ⋅ Jun-Yan He ⋅ Rui Yang ⋅ Jie Hu ⋅ Xiaojiang Peng ⋅ Lin Ma ⋅ Xiaoming Wei ⋅ Xiu Li
What to Forget in Unlearning? Forget Set Curation for Language Models
Animesh Jha ⋅ Arpandeep Khatua ⋅ Youssef Allouah ⋅ Sanmi Koyejo
What to Forget in Unlearning? Forget Set Curation for Language Models
Animesh Jha ⋅ Arpandeep Khatua ⋅ Youssef Allouah ⋅ Sanmi Koyejo
Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds
Guoji Fu ⋅ Taiji Suzuki ⋅ Wee Sun Lee ⋅ Atsushi Nitanda
Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds
Guoji Fu ⋅ Taiji Suzuki ⋅ Wee Sun Lee ⋅ Atsushi Nitanda
Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling
Yu Yao ⋅ Huanjian Zhou ⋅ Andi Han ⋅ Wei Huang ⋅ Masashi Sugiyama
Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling
Yu Yao ⋅ Huanjian Zhou ⋅ Andi Han ⋅ Wei Huang ⋅ Masashi Sugiyama
A Unified Perspective on Task Retrieval and Learning in In-Context Learning on Markov Data
Peng Wang ⋅ Huikang Liu ⋅ Zhiyuan Huang ⋅ Wendong Li ⋅ Po Chen ⋅ Rujun Jiang
A Unified Perspective on Task Retrieval and Learning in In-Context Learning on Markov Data
Peng Wang ⋅ Huikang Liu ⋅ Zhiyuan Huang ⋅ Wendong Li ⋅ Po Chen ⋅ Rujun Jiang
Prior Dominance in Audio-Visual LLMs: When Generative Models Memorize Over Reasoning Under Cross-modal Conflict
Adarsh Sudheer ⋅ David Li ⋅ Omar El-Banna ⋅ Ishaan Kodarapu ⋅ Arjun Bahuguna ⋅ Vasu Sharma
Prior Dominance in Audio-Visual LLMs: When Generative Models Memorize Over Reasoning Under Cross-modal Conflict
Adarsh Sudheer ⋅ David Li ⋅ Omar El-Banna ⋅ Ishaan Kodarapu ⋅ Arjun Bahuguna ⋅ Vasu Sharma
Memorization Detection in Diffusion Models via Text Embedding Interpolation
Changsu Shin ⋅ Jinseong Park ⋅ Sungyoon Lee
Memorization Detection in Diffusion Models via Text Embedding Interpolation
Changsu Shin ⋅ Jinseong Park ⋅ Sungyoon Lee
Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data
Yunlong Hou ⋅ Fengzhuo Zhang ⋅ Yuan Cheng ⋅ Jiachun Pan ⋅ Xingyao Li ⋅ Zhuoran Yang
Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data
Yunlong Hou ⋅ Fengzhuo Zhang ⋅ Yuan Cheng ⋅ Jiachun Pan ⋅ Xingyao Li ⋅ Zhuoran Yang
Unlocking the Duality between Flow and Field Matching
Daniil Shlenskii ⋅ Alexander Varlamov ⋅ Nazar Buzun ⋅ Aleksandr Korotin
Unlocking the Duality between Flow and Field Matching
Daniil Shlenskii ⋅ Alexander Varlamov ⋅ Nazar Buzun ⋅ Aleksandr Korotin
Temporal Backtracking Search for Test-time Generative Video Reasoning
Sejoon Jun ⋅ Zheng Ding ⋅ Huangyuan Su ⋅ Weirui Ye ⋅ Yilun Du
Temporal Backtracking Search for Test-time Generative Video Reasoning
Sejoon Jun ⋅ Zheng Ding ⋅ Huangyuan Su ⋅ Weirui Ye ⋅ Yilun Du
Local Manifold Identification with Latent Linear Models and OT Flows
Sherman Khoo ⋅ Song Liu ⋅ Mark Beaumont
Local Manifold Identification with Latent Linear Models and OT Flows
Sherman Khoo ⋅ Song Liu ⋅ Mark Beaumont
ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing
Yixuan Jia ⋅ Siyi Chen ⋅ Yida Pan ⋅ Xiao Li ⋅ Lianghe Shi ⋅ Chanyong Jung ⋅ Haijie Yuan ⋅ Ismail Alkhouri ⋅ Yue C Wu ⋅ Saiprasad Ravishankar ⋅ Jeffrey Fessler ⋅ Qing Qu
ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing
Yixuan Jia ⋅ Siyi Chen ⋅ Yida Pan ⋅ Xiao Li ⋅ Lianghe Shi ⋅ Chanyong Jung ⋅ Haijie Yuan ⋅ Ismail Alkhouri ⋅ Yue C Wu ⋅ Saiprasad Ravishankar ⋅ Jeffrey Fessler ⋅ Qing Qu
Internal Data Repetition Destroys Language Models
Jessica Chudnovsky ⋅ Joshua Kazdan ⋅ Noam Levi ⋅ Rylan Schaeffer ⋅ Yegor Denisov-Blanch ⋅ Sanmi Koyejo ⋅ David Donoho
Internal Data Repetition Destroys Language Models
Jessica Chudnovsky ⋅ Joshua Kazdan ⋅ Noam Levi ⋅ Rylan Schaeffer ⋅ Yegor Denisov-Blanch ⋅ Sanmi Koyejo ⋅ David Donoho
What You Predict Shapes How You Memorize: Target-Parameterization and Memorization Dynamics in Flow Matching
Mohammed Al-Jaff ⋅ Amir Mehrpanah ⋅ Gustav Eje Henter ⋅ Hossein Azizpour ⋅ Danica Kragic
What You Predict Shapes How You Memorize: Target-Parameterization and Memorization Dynamics in Flow Matching
Mohammed Al-Jaff ⋅ Amir Mehrpanah ⋅ Gustav Eje Henter ⋅ Hossein Azizpour ⋅ Danica Kragic
Why Does Pruning during Training Work? A Signal-to-Noise Analysis of Sparse Neural Network Training
Shiyuan Ren ⋅ Jiarui Jiang ⋅ Miao Zhang ⋅ Xiang Deng ⋅ Min zhang ⋅ Liqiang Nie
Why Does Pruning during Training Work? A Signal-to-Noise Analysis of Sparse Neural Network Training
Shiyuan Ren ⋅ Jiarui Jiang ⋅ Miao Zhang ⋅ Xiang Deng ⋅ Min zhang ⋅ Liqiang Nie
Manifold-Guided Attention Steering
Ian Li ⋅ Kapilesh Guruprasad ⋅ Raunak Sengupta ⋅ Ninad Satish ⋅ Loris D'Antoni ⋅ Rose Yu
Manifold-Guided Attention Steering
Ian Li ⋅ Kapilesh Guruprasad ⋅ Raunak Sengupta ⋅ Ninad Satish ⋅ Loris D'Antoni ⋅ Rose Yu
A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
Moongyu Jeon ⋅ Sangwoo Shin ⋅ Bumjun Kim ⋅ Kyelim Lee ⋅ Albert No
A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
Moongyu Jeon ⋅ Sangwoo Shin ⋅ Bumjun Kim ⋅ Kyelim Lee ⋅ Albert No
Test of Time: Rethinking Temporal Signal of Benchmark Contamination
Terry Zhang ⋅ Gopal Dev ⋅ Ning Wang ⋅ Max Obreiter ⋅ Wenyuan Jiang ⋅ Punya Pandey ⋅ Keenan Samway ⋅ Yinya Huang ⋅ Bernhard Schölkopf ⋅ Mrinmaya Sachan ⋅ Zhijing Jin
Test of Time: Rethinking Temporal Signal of Benchmark Contamination
Terry Zhang ⋅ Gopal Dev ⋅ Ning Wang ⋅ Max Obreiter ⋅ Wenyuan Jiang ⋅ Punya Pandey ⋅ Keenan Samway ⋅ Yinya Huang ⋅ Bernhard Schölkopf ⋅ Mrinmaya Sachan ⋅ Zhijing Jin
Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
Yu-Du Feng ⋅ Niels Mündler ⋅ Mark Vero ⋅ Martin Vechev
Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
Yu-Du Feng ⋅ Niels Mündler ⋅ Mark Vero ⋅ Martin Vechev
Demystifying the Slash Pattern in Attention: The Role of RoPE
Yuan Cheng ⋅ Fengzhuo Zhang ⋅ Yunlong Hou ⋅ Cunxiao Du ⋅ Chao Du ⋅ Tianyu Pang ⋅ Aixin Sun ⋅ Zhuoran Yang
Demystifying the Slash Pattern in Attention: The Role of RoPE
Yuan Cheng ⋅ Fengzhuo Zhang ⋅ Yunlong Hou ⋅ Cunxiao Du ⋅ Chao Du ⋅ Tianyu Pang ⋅ Aixin Sun ⋅ Zhuoran Yang
Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics
Matthew Smart ⋅ Soumya Ganguly ⋅ Nilava Metya ⋅ Alexandre V Morozov ⋅ Anirvan Sengupta
Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics
Matthew Smart ⋅ Soumya Ganguly ⋅ Nilava Metya ⋅ Alexandre V Morozov ⋅ Anirvan Sengupta
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Qihan Ren ⋅ Wang Peng ⋅ Ruikun Cai ⋅ Shuai Shao ⋅ Dadi Guo ⋅ Yuejin Xie ⋅ Yafu Li ⋅ Quanshi Zhang ⋅ Xia Hu ⋅ Jing Shao ⋅ Dongrui Liu
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Qihan Ren ⋅ Wang Peng ⋅ Ruikun Cai ⋅ Shuai Shao ⋅ Dadi Guo ⋅ Yuejin Xie ⋅ Yafu Li ⋅ Quanshi Zhang ⋅ Xia Hu ⋅ Jing Shao ⋅ Dongrui Liu
Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoders
Benjamin Rozonoyer ⋅ Chong You ⋅ Michael Boratko ⋅ Himanshu Jain ⋅ Nilesh Gupta ⋅ Srinadh Bhojanapalli ⋅ Andrew McCallum ⋅ Felix X Yu
Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoders
Benjamin Rozonoyer ⋅ Chong You ⋅ Michael Boratko ⋅ Himanshu Jain ⋅ Nilesh Gupta ⋅ Srinadh Bhojanapalli ⋅ Andrew McCallum ⋅ Felix X Yu
Understanding Flatness in Generative Models: Its Role and Benefits
Taehwan Lee ⋅ Kyeongkook Seo ⋅ Jaejun Yoo ⋅ Sung Whan Yoon
Understanding Flatness in Generative Models: Its Role and Benefits
Taehwan Lee ⋅ Kyeongkook Seo ⋅ Jaejun Yoo ⋅ Sung Whan Yoon
Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data
Bao Pham ⋅ Mohammed Zaki ⋅ Luca Ambrogioni ⋅ Dmitry Krotov ⋅ Matteo Negri
Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data
Bao Pham ⋅ Mohammed Zaki ⋅ Luca Ambrogioni ⋅ Dmitry Krotov ⋅ Matteo Negri
Training In-Context and In-Weights Mixtures Via Contrastive Context Sampling
Deevyanshu Malu ⋅ Deeptanshu Malu ⋅ Sunita Sarawagi ⋅ Aditya Nemiwal
Training In-Context and In-Weights Mixtures Via Contrastive Context Sampling
Deevyanshu Malu ⋅ Deeptanshu Malu ⋅ Sunita Sarawagi ⋅ Aditya Nemiwal
Midpoint Generative Models
Daniil Shlenskii ⋅ Nikita Gushchin ⋅ Lev Novitskiy ⋅ Dmitry V. Dylov ⋅ Aleksandr Korotin
Midpoint Generative Models
Daniil Shlenskii ⋅ Nikita Gushchin ⋅ Lev Novitskiy ⋅ Dmitry V. Dylov ⋅ Aleksandr Korotin
Blind denoising diffusion models and adaptive sampling algorithms
Zahra Kadkhodaie ⋅ Aram-Alexandre Pooladian ⋅ Sinho Chewi ⋅ Eero Simoncelli
Blind denoising diffusion models and adaptive sampling algorithms
Zahra Kadkhodaie ⋅ Aram-Alexandre Pooladian ⋅ Sinho Chewi ⋅ Eero Simoncelli
Beyond Pixel Space: Frequency-Domain Uncertainty for Structure Aware Diffusion Guidance
Tianqi Zhao ⋅ Xixi Liu ⋅ Yingzhen Li ⋅ Zhengrui Xiang ⋅ Liangrui Peng
Beyond Pixel Space: Frequency-Domain Uncertainty for Structure Aware Diffusion Guidance
Tianqi Zhao ⋅ Xixi Liu ⋅ Yingzhen Li ⋅ Zhengrui Xiang ⋅ Liangrui Peng
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Yaxuan Li ⋅ Yuxin Zuo ⋅ Bingxiang He ⋅ Jinqian Zhang ⋅ Chaojun Xiao ⋅ Cheng Qian ⋅ Tianyu Yu ⋅ Huan-ang Gao ⋅ Wenkai Yang ⋅ Zhiyuan Liu ⋅ Ning Ding
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Yaxuan Li ⋅ Yuxin Zuo ⋅ Bingxiang He ⋅ Jinqian Zhang ⋅ Chaojun Xiao ⋅ Cheng Qian ⋅ Tianyu Yu ⋅ Huan-ang Gao ⋅ Wenkai Yang ⋅ Zhiyuan Liu ⋅ Ning Ding
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
Xiao Li ⋅ Yixuan Jia ⋅ Zekai Zhang ⋅ Xiang Li ⋅ Lianghe Shi ⋅ Jinxin Zhou ⋅ Zhihui Zhu ⋅ Liyue Shen ⋅ Qing Qu
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
Xiao Li ⋅ Yixuan Jia ⋅ Zekai Zhang ⋅ Xiang Li ⋅ Lianghe Shi ⋅ Jinxin Zhou ⋅ Zhihui Zhu ⋅ Liyue Shen ⋅ Qing Qu
Masked Distillation: Internalizing Chain-of-Thought in Small Language Models
Durgesh Kalwar ⋅ Vardhan Palod ⋅ Subbarao Kambhampati
Masked Distillation: Internalizing Chain-of-Thought in Small Language Models
Durgesh Kalwar ⋅ Vardhan Palod ⋅ Subbarao Kambhampati
Registers Matter for Pixel-space Diffusion Transformers
Nikita Starodubcev ⋅ Ilia Sudakov ⋅ Ilya Drobyshevskiy ⋅ Artem Babenko ⋅ Dmitry Baranchuk
Registers Matter for Pixel-space Diffusion Transformers
Nikita Starodubcev ⋅ Ilia Sudakov ⋅ Ilya Drobyshevskiy ⋅ Artem Babenko ⋅ Dmitry Baranchuk
Interpreting Latent CoT Reasoning as Dynamical Systems
Shreya Sanjay Boyane ⋅ Sabari I Duraipandian ⋅ Manju Nagesh ⋅ Jerome Francis ⋅ Archana Vaidheeswaran ⋅ Kevin Zhu
Interpreting Latent CoT Reasoning as Dynamical Systems
Shreya Sanjay Boyane ⋅ Sabari I Duraipandian ⋅ Manju Nagesh ⋅ Jerome Francis ⋅ Archana Vaidheeswaran ⋅ Kevin Zhu
Amortising Bayesian Experimental Design for Sequential Information Gathering in LLMs
Jakob Hartmann ⋅ James Harvey ⋅ Jhonathan Navott ⋅ Erik Wang ⋅ Luckeciano C. Melo ⋅ Flaviu Cipcigan ⋅ Cheng Zhang ⋅ Alessandro Abate
Amortising Bayesian Experimental Design for Sequential Information Gathering in LLMs
Jakob Hartmann ⋅ James Harvey ⋅ Jhonathan Navott ⋅ Erik Wang ⋅ Luckeciano C. Melo ⋅ Flaviu Cipcigan ⋅ Cheng Zhang ⋅ Alessandro Abate
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
Victor Conchello Vendrell ⋅ Arnau Padres Masdemont ⋅ Niccolò Grillo ⋅ Jordi Ros-Giralt ⋅ Arash Behboodi ⋅ Fabio Valerio Massoli
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
Victor Conchello Vendrell ⋅ Arnau Padres Masdemont ⋅ Niccolò Grillo ⋅ Jordi Ros-Giralt ⋅ Arash Behboodi ⋅ Fabio Valerio Massoli
FERMI: Feature-Mapping for Relational Membership Inference on Tabular Diffusion Models
Abtin Mahyar ⋅ Masoumeh Shafieinejad ⋅ Yuhan Liu ⋅ Xi He
FERMI: Feature-Mapping for Relational Membership Inference on Tabular Diffusion Models
Abtin Mahyar ⋅ Masoumeh Shafieinejad ⋅ Yuhan Liu ⋅ Xi He
Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
Advaith Ravishankar ⋅ Serena Liu ⋅ Mingyang Wang ⋅ Todd Zhou ⋅ Jeffrey Zhou ⋅ Arnav Sharma ⋅ Ziling Hu ⋅ Léopold Das ⋅ Abdulaziz Sobirov ⋅ Faizaan Siddique ⋅ Freddy Yu ⋅ Julia S Baek ⋅ Yan Luo ⋅ Mengyu Wang
Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
Advaith Ravishankar ⋅ Serena Liu ⋅ Mingyang Wang ⋅ Todd Zhou ⋅ Jeffrey Zhou ⋅ Arnav Sharma ⋅ Ziling Hu ⋅ Léopold Das ⋅ Abdulaziz Sobirov ⋅ Faizaan Siddique ⋅ Freddy Yu ⋅ Julia S Baek ⋅ Yan Luo ⋅ Mengyu Wang
Learned Relay Representations for Forward-Thinking Discrete Diffusion Models
Benjamin Rozonoyer ⋅ Jacopo Minniti ⋅ Dhruvesh Patel ⋅ Neil Band ⋅ Joey Bose ⋅ Tim G. J. Rudner ⋅ Andrew McCallum
Learned Relay Representations for Forward-Thinking Discrete Diffusion Models
Benjamin Rozonoyer ⋅ Jacopo Minniti ⋅ Dhruvesh Patel ⋅ Neil Band ⋅ Joey Bose ⋅ Tim G. J. Rudner ⋅ Andrew McCallum
Rethinking On-Policy Self-Distillation for Thinking Models
Simran Kaur ⋅ Narutatsu Ri ⋅ Yinghui He ⋅ Liam Fowl ⋅ Sanjeev Arora
Rethinking On-Policy Self-Distillation for Thinking Models
Simran Kaur ⋅ Narutatsu Ri ⋅ Yinghui He ⋅ Liam Fowl ⋅ Sanjeev Arora
Just Add More Capacitors: Eliminating Flux Leakage in Electrostatic Field Matching
Daniil Shlenskii ⋅ S. I Manukhov ⋅ Alexander Kolesov ⋅ Alexander Varlamov ⋅ Nazar Buzun ⋅ V.V. Palyulin ⋅ Aleksandr Korotin
Just Add More Capacitors: Eliminating Flux Leakage in Electrostatic Field Matching
Daniil Shlenskii ⋅ S. I Manukhov ⋅ Alexander Kolesov ⋅ Alexander Varlamov ⋅ Nazar Buzun ⋅ V.V. Palyulin ⋅ Aleksandr Korotin
Learn from Your Mistakes: Self-Correcting Masked Diffusion Models
Yair Schiff ⋅ Omer Belhasin ⋅ Roy Uziel ⋅ Guanghan Wang ⋅ Marianne Arriola ⋅ Gilad Turok ⋅ Ran Zilberstein ⋅ Michael Elad ⋅ Volodymyr Kuleshov
Learn from Your Mistakes: Self-Correcting Masked Diffusion Models
Yair Schiff ⋅ Omer Belhasin ⋅ Roy Uziel ⋅ Guanghan Wang ⋅ Marianne Arriola ⋅ Gilad Turok ⋅ Ran Zilberstein ⋅ Michael Elad ⋅ Volodymyr Kuleshov
Tracing Uncertainty in Language Model "Reasoning"
Nils Grünefeld ⋅ Bertram Højer ⋅ Philipp Mondorf ⋅ Barbara Plank ⋅ Anna Rogers ⋅ Christian Hardmeier ⋅ Stefan Heinrich ⋅ Jes Frellsen
Tracing Uncertainty in Language Model "Reasoning"
Nils Grünefeld ⋅ Bertram Højer ⋅ Philipp Mondorf ⋅ Barbara Plank ⋅ Anna Rogers ⋅ Christian Hardmeier ⋅ Stefan Heinrich ⋅ Jes Frellsen
ReCAST: Probing Sparse Reference Use in In-Context Image Generation
YeonGyu Han ⋅ Junah Jung ⋅ Dongheon Lee
ReCAST: Probing Sparse Reference Use in In-Context Image Generation
YeonGyu Han ⋅ Junah Jung ⋅ Dongheon Lee
Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning
Prakhar Gupta ⋅ Garv Shah ⋅ Satyam Goyal ⋅ Anirudh Kanchi
Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning
Prakhar Gupta ⋅ Garv Shah ⋅ Satyam Goyal ⋅ Anirudh Kanchi
Inverse-Confidence Sampling for Continuous Diffusion Language Models
Andrei Rekesh ⋅ Jarrid Rector-Brooks ⋅ Chenghao Liu
Inverse-Confidence Sampling for Continuous Diffusion Language Models
Andrei Rekesh ⋅ Jarrid Rector-Brooks ⋅ Chenghao Liu
Understanding LLM generalization through fine-tuning
Harshul Basava ⋅ Shih Ee Whang ⋅ Keshav Shenoy ⋅ Emil Ryd
Understanding LLM generalization through fine-tuning
Harshul Basava ⋅ Shih Ee Whang ⋅ Keshav Shenoy ⋅ Emil Ryd
Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models
Siyuan Zhang ⋅ Jialian Li ⋅ Yichi Zhang ⋅ Xiao Yang ⋅ Yinpeng Dong ⋅ Hang Su
Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models
Siyuan Zhang ⋅ Jialian Li ⋅ Yichi Zhang ⋅ Xiao Yang ⋅ Yinpeng Dong ⋅ Hang Su
Quantifying the Effect of Test Set Contamination on Generative Evaluations
Rylan Schaeffer ⋅ Joshua Kazdan ⋅ Baber Abbasi ⋅ Ken Ziyu Liu ⋅ Brando Miranda ⋅ Ahmed Ahmed ⋅ Fazl Barez ⋅ Abhay Puri ⋅ Stella Biderman ⋅ Niloofar Mireshghallah ⋅ Sanmi Koyejo
Quantifying the Effect of Test Set Contamination on Generative Evaluations
Rylan Schaeffer ⋅ Joshua Kazdan ⋅ Baber Abbasi ⋅ Ken Ziyu Liu ⋅ Brando Miranda ⋅ Ahmed Ahmed ⋅ Fazl Barez ⋅ Abhay Puri ⋅ Stella Biderman ⋅ Niloofar Mireshghallah ⋅ Sanmi Koyejo
Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation
Young Kyung Kim ⋅ Oded Schlesinger ⋅ Yuzhou Zhao ⋅ J. M Di Martino ⋅ Guillermo Sapiro
Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation
Young Kyung Kim ⋅ Oded Schlesinger ⋅ Yuzhou Zhao ⋅ J. M Di Martino ⋅ Guillermo Sapiro
Benign Overfitting Does Not Occur in Diffusion Models
Tyler Farghly ⋅ Benjamin Dupuis ⋅ Alain Oliviero Durmus ⋅ Umut Simsekli
Benign Overfitting Does Not Occur in Diffusion Models
Tyler Farghly ⋅ Benjamin Dupuis ⋅ Alain Oliviero Durmus ⋅ Umut Simsekli
Scaling with Recursion in Masked Discrete Diffusion Models
Alba Carballo-Castro ⋅ Julianna Piskorz ⋅ Paulius Rauba ⋅ Mihaela van der Schaar ⋅ Pascal Frossard
Scaling with Recursion in Masked Discrete Diffusion Models
Alba Carballo-Castro ⋅ Julianna Piskorz ⋅ Paulius Rauba ⋅ Mihaela van der Schaar ⋅ Pascal Frossard
Evaluating Spatial World Modeling in Video \\ Generators via 3D Camera Trajectory Generation
Tianlong Wang ⋅ Lehan Yang ⋅ Yuheng Liu ⋅ Hanzhang Yuan ⋅ Wenhao Zhang ⋅ Pinqiao Wang ⋅ Yifan Li ⋅ Yu Kong ⋅ Sheng Li
Evaluating Spatial World Modeling in Video \\ Generators via 3D Camera Trajectory Generation
Tianlong Wang ⋅ Lehan Yang ⋅ Yuheng Liu ⋅ Hanzhang Yuan ⋅ Wenhao Zhang ⋅ Pinqiao Wang ⋅ Yifan Li ⋅ Yu Kong ⋅ Sheng Li
Learning Manifold Data with Flow Matching
Sophia Pi ⋅ Mingcheng Lu ⋅ Jerry Yao-Chieh Hu ⋅ Maojiang Su ⋅ Weimin Wu ⋅ Han Liu
Learning Manifold Data with Flow Matching
Sophia Pi ⋅ Mingcheng Lu ⋅ Jerry Yao-Chieh Hu ⋅ Maojiang Su ⋅ Weimin Wu ⋅ Han Liu
Why is A+B Better Than B? A Simple Graph Perspective on Task Transfer
Dang Nguyen ⋅ Jianhao Huang ⋅ Ali Payani ⋅ Baharan Mirzasoleiman
Why is A+B Better Than B? A Simple Graph Perspective on Task Transfer
Dang Nguyen ⋅ Jianhao Huang ⋅ Ali Payani ⋅ Baharan Mirzasoleiman
Learning Human Habits with Rule-Guided Active Inference
Zhiren Gong ⋅ Chao Yang ⋅ Wendi Ren ⋅ Shuang Li
Learning Human Habits with Rule-Guided Active Inference
Zhiren Gong ⋅ Chao Yang ⋅ Wendi Ren ⋅ Shuang Li
What Architectural Inductive Bias Makes Diffusion Models Succeed? A Perspective from the Implicit Regularization of Gradient Descent
Tongtong Liang ⋅ Esha Singh ⋅ Rahul Parhi ⋅ Alexander Cloninger ⋅ Yu-Xiang Wang
What Architectural Inductive Bias Makes Diffusion Models Succeed? A Perspective from the Implicit Regularization of Gradient Descent
Tongtong Liang ⋅ Esha Singh ⋅ Rahul Parhi ⋅ Alexander Cloninger ⋅ Yu-Xiang Wang
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
Andrei Nicolicioiu ⋅ Mohammad Pezeshki ⋅ Aaron Courville
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
Andrei Nicolicioiu ⋅ Mohammad Pezeshki ⋅ Aaron Courville
TIGER: Bridging the Multimodal Reasoning-Access Gap via Modality Counterfactuals
Gregory Kang Ruey Lau ⋅ Huynh Minh Nguyen ⋅ Bryan Kian Hsiang Low
TIGER: Bridging the Multimodal Reasoning-Access Gap via Modality Counterfactuals
Gregory Kang Ruey Lau ⋅ Huynh Minh Nguyen ⋅ Bryan Kian Hsiang Low
In- and Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks
Yannic Neuhaus ⋅ Chanoknan Tanchotikul ⋅ Nicolas Flammarion ⋅ Matthias Hein ⋅ Francesco Croce
In- and Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks
Yannic Neuhaus ⋅ Chanoknan Tanchotikul ⋅ Nicolas Flammarion ⋅ Matthias Hein ⋅ Francesco Croce
Relative Score Policy Optimization for Diffusion Language Models
Zichao Yu ⋅ Shengze Xu ⋅ Bingqing Jiang ⋅ Wenyi Zhang ⋅ Difan Zou
Relative Score Policy Optimization for Diffusion Language Models
Zichao Yu ⋅ Shengze Xu ⋅ Bingqing Jiang ⋅ Wenyi Zhang ⋅ Difan Zou
In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration
Youngbin Choi ⋅ Minjong Lee ⋅ Saemi Moon ⋅ Seunghyuk Cho ⋅ Chaehyeon Chung ⋅ MoonJeong Park ⋅ Dongwoo Kim
In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration
Youngbin Choi ⋅ Minjong Lee ⋅ Saemi Moon ⋅ Seunghyuk Cho ⋅ Chaehyeon Chung ⋅ MoonJeong Park ⋅ Dongwoo Kim
Understanding Generalization in Diffusion Distillation via Probability Flow Distance
Huijie Zhang ⋅ Zijian Huang ⋅ Siyi Chen ⋅ Jinfan Zhou ⋅ Zekai Zhang ⋅ Peng Wang ⋅ Qing Qu
Understanding Generalization in Diffusion Distillation via Probability Flow Distance
Huijie Zhang ⋅ Zijian Huang ⋅ Siyi Chen ⋅ Jinfan Zhou ⋅ Zekai Zhang ⋅ Peng Wang ⋅ Qing Qu
The Surprising Effectiveness of Deleting Weights in LLM Reasoning and Adaptation
Jack Lu ⋅ Zhenbang Yang ⋅ Mike Lasby ⋅ Tejas Pote ⋅ Yani Ioannou ⋅ Mengye Ren
The Surprising Effectiveness of Deleting Weights in LLM Reasoning and Adaptation
Jack Lu ⋅ Zhenbang Yang ⋅ Mike Lasby ⋅ Tejas Pote ⋅ Yani Ioannou ⋅ Mengye Ren
How to Train Your Latent Diffusion Language Model Jointly With the Latent Space
Viacheslav Meshchaninov ⋅ Alexander Shabalin ⋅ Egor Chimbulatov ⋅ Nikita Gushchin ⋅ Ilya Koziev ⋅ Aleksandr Korotin ⋅ Dmitry Vetrov
How to Train Your Latent Diffusion Language Model Jointly With the Latent Space
Viacheslav Meshchaninov ⋅ Alexander Shabalin ⋅ Egor Chimbulatov ⋅ Nikita Gushchin ⋅ Ilya Koziev ⋅ Aleksandr Korotin ⋅ Dmitry Vetrov
Fine-Tuning Dynamics of In-Context Factual Recall in Transformers
Ruomin Huang ⋅ Eshaan Nichani ⋅ Jason Lee ⋅ Rong Ge
Fine-Tuning Dynamics of In-Context Factual Recall in Transformers
Ruomin Huang ⋅ Eshaan Nichani ⋅ Jason Lee ⋅ Rong Ge
ExeDream: Grounding Video Generation Models in Physical World via Robot Execution
Rui Zhao ⋅ Kaiming Yang ⋅ Jifeng Zhu ⋅ Siyang Chen ⋅ Ziqi Wang ⋅ Weijia Wu ⋅ Kevin Qinghong Lin ⋅ Mike Zheng Shou
ExeDream: Grounding Video Generation Models in Physical World via Robot Execution
Rui Zhao ⋅ Kaiming Yang ⋅ Jifeng Zhu ⋅ Siyang Chen ⋅ Ziqi Wang ⋅ Weijia Wu ⋅ Kevin Qinghong Lin ⋅ Mike Zheng Shou
DVD: Deterministic Video Depth Estimation with Generative Priors
Hongfei (Faye) Zhang ⋅ Harold Haodong Chen ⋅ Chenfei Liao ⋅ Jing He ⋅ Zixin Zhang ⋅ Haodong Li ⋅ Yihao Liang ⋅ Kanghao Chen ⋅ Bin Ren ⋅ Xu Zheng ⋅ Shuai Yang ⋅ Kun Zhou ⋅ Yinchuan Li ⋅ Nicu Sebe ⋅ YINGCONG CHEN
DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmasking
Gilad Turok ⋅ Yair Schiff ⋅ Chris De Sa ⋅ Volodymyr Kuleshov
Sobolev Regularized Score Difference Estimation in Diffusion Models
Chenghan Xie ⋅ Jose Blanchet ⋅ Renyuan Xu
Fixed-Point Reasoning: Stable and Adaptive Deep Looped Models
Sajad Movahedi ⋅ Shlomo L Feigin ⋅ Vera Milovanović ⋅ Alexander Theus ⋅ Thomas Hofmann ⋅ Valentina Boeva ⋅ T. Konstantin Rusch ⋅ Antonio Orvieto
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
Yinghui He ⋅ Simran Kaur ⋅ Adithya Bhaskar ⋅ Yongjin Yang ⋅ Jiarui Liu ⋅ Narutatsu Ri ⋅ Liam Fowl ⋅ Abhishek Panigrahi ⋅ Danqi Chen ⋅ Sanjeev Arora
Internal Tree Search Execution in Transformers
Hibiki FUKUSHIMA ⋅ Taiji Suzuki
Frontier Learning: Training LLM Reasoners at the Edge of Capability
Shyam Sundhar Ramesh ⋅ Robin Faro ⋅ Enea Monzio Compagnoni ⋅ Ilija Bogunovic ⋅ Aurelien Lucchi
Chain-of-Thought Gradient Descent
Hong-Yu Chen ⋅ Venkat Ganti ⋅ Jerry Yao-Chieh Hu ⋅ Hude Liu ⋅ Han Liu
Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules
Riccardo De Santi ⋅ Bruce D Lee ⋅ Cristian P Jensen ⋅ Kimon Protopapas ⋅ Sophia Tang ⋅ Chenghao Liu ⋅ Pranam Chatterjee, PhD ⋅ Yisong Yue ⋅ Andreas Krause
Feedforward Mixing is as Sharp as it is Slow in Reverse
Benedict Aaron Tjandra ⋅ Avi Wigderson ⋅ João Madeira Araujo ⋅ Oleksandr Vitvitskyi ⋅ Federico Barbero ⋅ Petar Veličković
Beyond Raw Competence: Logical Equivariance in Diffusion Language Models
Sunwoo Hong ⋅ Seo Hyun Kim ⋅ Younwoo Choi ⋅ Chen-Hao Chao ⋅ Se-Young Yun ⋅ Rahul G. Krishnan
The Distillation Game: Adaptive Attacks & Efficient Defenses
Youssef Allouah ⋅ Mahdi Haghifam ⋅ Sanmi Koyejo ⋅ Reza Shokri
A Theoretical Analysis of Curriculum Training in Diffusion Models
Jiawei Sun ⋅ Shuai Zhang ⋅ Hongkang Li ⋅ Sijia Liu ⋅ Pin-Yu Chen ⋅ Meng Wang
Solve the Loop: Attractor Models for Language and Reasoning
Jacob Fein-Ashley ⋅ Paria Rashidinejad
An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms
Nils Grünefeld ⋅ Jes Frellsen ⋅ Christian Hardmeier
LLM-WikiRace: A Benchmark for Planning and Reasoning over Real-World Knowledge Graphs
Juliusz Ziomek ⋅ William Bankes ⋅ Lorenz Wolf ⋅ Shyam Sundhar Ramesh ⋅ Xiaohang Tang ⋅ Ilija Bogunovic
Forward-Chaining Temporal Point Process
Chao Yang ⋅ Wendi Ren ⋅ Shuang Li
LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
Yuxin Chen ⋅ Chumeng Liang ⋅ Hangke Sui ⋅ Ruihan Guo ⋅ Chaoran Cheng ⋅ Jiaxuan You ⋅ Ge Liu
LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
Yuxin Chen ⋅ Chumeng Liang ⋅ Hangke Sui ⋅ Ruihan Guo ⋅ Chaoran Cheng ⋅ Jiaxuan You ⋅ Ge Liu
Compositional Flow Matching with Factored Velocity Fields
Avery H Ryoo ⋅ Dane Malenfant ⋅ Matthew Perich ⋅ Guillaume Lajoie
On the approximation of Schrödinger bridge potentials
Denis Belomestny ⋅ Alexey Naumov ⋅ Nikita Puchkin ⋅ Denis Suchkov
When Does Diffusion Purification Amplify Perturbations?
Haibo Zhang ⋅ Saiyue Lyu ⋅ Yuntao Wang ⋅ Takeshi Saitoh
TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models
Arseny Ivanov ⋅ Sergei Kholkin ⋅ Vladislav Gromadskii ⋅ Grigoriy Ksenofontov ⋅ Ivan Oseledets ⋅ Aleksandr Korotin
Growing Images: Spatial Scheduling in Diffusion Inpainting
Matteo Vilucchio ⋅ Luca Pesce ⋅ FLORENT KRZAKALA
Few-Shot Learning in Video Diffusion Models
Pablo Acuaviva ⋅ Aram Davtyan ⋅ Mariam Hassan ⋅ Sebastian Stapf ⋅ Ahmad Rahimi ⋅ Alexandre Alahi ⋅ Paolo Favaro
Unlearning for One-Step Generative Models via Unbalanced Optimal Transport
Hyundo Choi ⋅ Junhyeong An ⋅ Jinseong Park ⋅ Jaewoong Choi
Spectral Signatures of Memorization in Diffusion Models: A Multi-Scale Diagnostic Study
Raghav Agarwal ⋅ Aayam Bansal ⋅ Ishaan Gangwani ⋅ Kabir Jain
Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs
Sudhanshu Agrawal ⋅ Risheek Garrepalli ⋅ Raghavv Goel ⋅ Christopher Lott ⋅ Fatih Porikli ⋅ Mingu Lee
Universality, Composition Generalization, and Algorithm Emulation All In-Context
Jerry Yao-Chieh Hu ⋅ Hong-Yu Chen ⋅ Po-Chiao Lin ⋅ Maojiang Su ⋅ Han Liu
Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories
Dake Bu ⋅ Wei Huang ⋅ Andi Han ⋅ Bo Xue ⋅ Hau-San Wong ⋅ Qingfu Zhang ⋅ Taiji Suzuki ⋅ Atsushi Nitanda
Scale Dependent Data Duplication
Joshua Kazdan ⋅ Noam Levi ⋅ Rylan Schaeffer ⋅ Jessica Chudnovsky ⋅ Abhay Puri ⋅ Bo He ⋅ Mehmet Donmez ⋅ Sanmi Koyejo ⋅ David Donoho
Do Thinking Tokens Help with Safety?
Narutatsu Ri ⋅ Abhishek Panigrahi ⋅ Sanjeev Arora
Local Coverage Governs Memorization in Diffusion Models
Claudia Merger ⋅ Sebastian Goldt
Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
Baris Askin ⋅ Muhammed Ustaomeroglu ⋅ Anupam Nayak ⋅ Gauri Joshi ⋅ Guannan Qu ⋅ Carlee Joe-Wong
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
Woojung Han ⋅ Seil Kang ⋅ Youngjun Jun ⋅ Min-Hung Chen ⋅ Fu-En Yang ⋅ Seong Jae Hwang
Generalization of Diffusion Models Arises with a Balanced Representation Space
Zekai Zhang ⋅ Xiao Li ⋅ Xiang Li ⋅ Lianghe Shi ⋅ Meng Wu ⋅ Molei Tao ⋅ Qing Qu
On approximation and estimation of Schrödinger potentials without the curse of dimensionality
Artsiom Patarusau ⋅ Nikita Puchkin ⋅ Konstantin Yakovlev
Personalized Privacy Control in LLMs via Attention Head Intervention
Junseok Kim ⋅ Nakyeong Yang ⋅ Kyomin Jung
Beyond Power Spectra: Cross-Frequency Interactions in Generative Dynamics
Amir Mehrpanah ⋅ Mohammed Al-Jaff ⋅ Matteo Gamba ⋅ Hossein Azizpour
Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation
Siyi Chen ⋅ Shaowei Liu ⋅ Yixuan Jia ⋅ Zian Wang ⋅ Huan Ling ⋅ Qing Qu ⋅ Jun Gao