Du 23 au 27 avril 2026, des dizaines de chercheuses et chercheurs de Mila participeront à la quatorzième International Conference on Learning Representations (ICLR 2026) à Rio de Janeiro, au Brésil. Cette année, elles et ils présenteront 70 articles scientifiques à la conférence principale et des dizaines de publications lors d’ateliers afin de partager les résultats de leur recherche en intelligence artificielle (IA) avec leurs pairs du monde entier.
Voici une liste de publications acceptées à ICLR 2026 contenant au moins un·e auteur·rice affilié·e à Mila.
Conférence principale
Unsupervised Representation Learning for 3D Mesh Parameterization with Semantic and Visibility Objectives: Amirhossein Zamani, Bruno Roy, Arianna Rampini
Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning: Marco Jiralerspong, Esther Derman, Danilo Vucetic, Nikolay Malkin, Bilun Sun, Tianyu Zhang, Pierre-Luc Bacon, Gauthier Gidel
Latent Veracity Inference for Identifying Errors in Stepwise Reasoning: Minsu Kim, Jean-Pierre Falet, Oliver Richardson, Xiaoyin Chen, Moksh Jain, Sungjin Ahn, Sungsoo Ahn, Yoshua Bengio
The Markovian Thinker: Milad Aghajohari, Kamran Chitsaz, Amirhossein Kazemnejad, Sarath Chandar, Alessandro Sordoni, Aaron Courville, Siva Reddy
Grounding Computer Use Agents on Human Demonstrations: Aarash Feizi, Shravan Nayak, Xiangru Jian, Kevin Qinghong Lin, Kaixin Li, Rabiul Awal, Xing Han Lu, Johan S Obando Ceron, Juan A. Rodriguez, Nicolas Chapados, David Vazquez, Adriana Romero-Soriano, Reihaneh Rabbany, Perouz Taslakian, Christopher Pal, Spandana Gella, Sai Rajeswar Mudumba
Fast Proteome-Scale Protein Interaction Retrieval via Residue-Level Factorization: Jianan Zhao, Zhihao Zhan, Narendra Chaudhary, Xinyu Yuan, Zuobai Zhang, Qian Cong, Jian Zhou, Sanchit Misra, Jian Tang
TGM: A Modular and Efficient Library for Machine Learning on Temporal Graphs: Jacob Chmura, Shenyang(Andy) Huang, Tran Gia Bao Ngo, Ali Parviz, Farimah Poursafaei, Jure Leskovec, Michael Bronstein, Guillaume Rabusseau, Matthias Fey, Reihaneh Rabbany
SelvaBox: A high‑resolution dataset for tropical tree crown detection: Hugo Baudchon, Arthur Ouaknine, Martin Weiss, Mélisande Teng, Thomas Walla, Antoine Caron-Guay, Christopher Pal, Etienne Laliberté
Efficient Regression-based Training of Normalizing Flows for Boltzmann Generators: Danyal Rehman, Oscar Davis, Jiarui Lu, Jian Tang, Michael Bronstein, Yoshua Bengio, Alexander Tong, Joey Bose
Simplicial Embeddings Improve Sample Efficiency in Actor–Critic Agents: Johan S Obando Ceron, Walter Mayor, Samuel Lavoie, Scott Fujimoto, Aaron Courville, Pablo Samuel Castro
Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations: Amin Soleimani Abyaneh, Charlotte Morissette, Mohamad H. Danesh, Anas Houssaini, David Meger, Gregory Dudek, Hsiu-Chin Lin
Towards All-Atom Foundation Models for Biomolecular Binding Affinity Prediction: Liang Shi, Zuobai Zhang, Huiyu Cai, Santiago Miret, Zhi Yang, Jian Tang
FALCON: Few-step Accurate Likelihoods for Continuous Flows: Danyal Rehman, Tara Akhound-Sadegh, Artem Gazizov, Yoshua Bengio, Alexander Tong
Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning: Jiashun Liu, Johan S Obando Ceron, Han Lu, Yancheng He, Weixun Wang, wenbo su, Bo Zheng, Pablo Samuel Castro, Aaron Courville, Ling Pan
The Geometry and Topology of Circuits: the Manifolds of Modular Addition: Gabriela Moisescu-Pareja, Gavin McCracken, Harley Wiltzer, Colin Daniels, Vincent Létourneau, Doina Precup, Jonathan Love
Self-Supervised Learning from Structural Invariance: Yipeng Zhang, Hafez Ghaemi, Jungyoon Lee, Shahab Bakhtiari, Eilif B Muller, Laurent Charlin
Robust Reward Modeling via Causal Rubrics: Pragya Srivastava, Harman Singh, Rahul Madhavan, Gandharv Patil, Sravanti Addepalli, Arun Suggala, Rengarajan Aravamudhan, Soumya Sharma, Anirban Laha, Aravindan Raghuveer, Karthikeyan Shanmugam, Doina Precup
Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute: Kieran Didi, Zuobai Zhang, Guoqing Zhou, Danny Reidenbach, Zhonglin Cao, Sooyoung Cha, Tomas Geffner, Christian Dallago, Jian Tang, Michael Bronstein, Martin Steinegger, Emine Kucukbenli, Arash Vahdat, Karsten Kreis
Towards Sustainable Investment Policies Informed by Opponent Shaping: Juan Duque, Razvan Ciuca, Ayoub Echchahed, Hugo Larochelle, Aaron Courville
Defining and quantifying compositional structure: Eric Elmoznino, Guillaume Lajoie
The Expressive Limits of Diagonal SSMs for State-Tracking: Mehran Shakerinava, Behnoush Khavari, Siamak Ravanbakhsh, Sarath Chandar
The Intricate Dance of Prompt Complexity, Quality, Diversity and Consistency in T2I Models: Zhang Xiaofeng, Aaron Courville, Michal Drozdzal, Adriana Romero-Soriano
Visual symbolic mechanisms: Emergent symbol processing in Vision Language Models: Rim Assouel, Declan Campbell, Yoshua Bengio, Taylor Webb
Dual Optimistic Ascent (PI Control) is the Augmented Lagrangian Method in Disguise: Juan Ramirez, Simon Lacoste-Julien
Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning: Daniel Lawson, Adriana Hugessen, Charlotte Cloutier, Glen Berseth, Khimya Khetarpal
ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning: Roger Creus Castanyer, Faisal Mohamed, Pablo Samuel Castro, Cyrus Neary, Glen Berseth
Learning From the Past with Cascading Eligibility Traces: Tokiniaina Raharison Ralambomihanta, Ivan Anokhin, Roman Pogodin, Samira Ebrahimi Kahou, Jonathan Cornford, Blake A Richards
OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction: Emily Jin, Andrei Nica, Kin Long Kelvin Lee, Joey Bose, Mikhail Galkin, Santiago Miret, Jarrid Rector-Brooks, Alexander Tong, Michael Bronstein, Frances Arnold, Chenghao Liu
SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate Modeling: Andrei Rekesh, Miruna Cretu, Dmytro Shevchuk, Pietro Lio, Robert Batey, Mike Tyers, Michał Koziarski, Chenghao Liu
LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks: Chuqin Geng, Ziyu Zhao, Zhaoyue Wang, Haolin Ye, Yuhe Jiang, Xujie Si
DRBench: A Realistic Benchmark for Enterprise Deep Research: Amirhossein Abaskohi, Tianyi Chen, Miguel Muñoz-Mármol, Curtis Fox, Amrutha Varshini Ramesh, Étienne Marcotte, Xing Han Lu, Nicolas Chapados, Spandana Gella, Christopher Pal, Alexandre Drouin, Issam dji
Benefits and Limitations of Communication in Multi-Agent Reasoning: Michael Rizvi-Martel, Satwik Bhattamishra, Neil Rathi, Guillaume Rabusseau, Michael Hahn
Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking: Ali Saheb Pasand, Elvis Dohmatob
$\mu$LO: Compute-Efficient Meta-Generalization of Learned Optimizers: Benjamin Thérien, Charles-Étienne Joseph, Boris Knyazev, Edouard Oyallon, Irina Rish, Eugene Belilovsky
Amortized Inference of Causal Models via Conditional Fixed-Point Iterations: Divyat Mahajan, Jannes Gladrow, Agrin Hilmkil, Cheng Zhang, Meyer Scetbon
Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries: Divyat Mahajan, Sachin Goyal, Badr Youbi Idrissi, Mohammad Pezeshki, Ioannis Mitliagkas, David Lopez-Paz, Kartik Ahuja
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction: Yusong Wu, Stephen Brade, Teng Ma, Tia-Jane Fowler, Enning Yang, Berker Banar, Aaron Courville, Natasha Jaques, Anna Huang
Towards Learned Optimization Free Lunch: Abhinav Moudgil, Boris Knyazev, Eugene Belilovsky
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training: Johannes von Oswald, Nino Scherrer, Seijin Kobayashi, Luca Versari, Songlin Yang, Maximilian Schlegel, Kaitlin Maile, Yanick Schimpf, Oliver Sieberling, Alexander Meulemans, Guillaume Lajoie, Rif A. Saurous, Charlotte Frenkel, Razvan Pascanu, Blaise Aguera y Arcas, Joao Sacramento
Property-Driven Protein Inverse Folding with Multi-Objective Preference Alignment: Junqi Liu, Xiaoyang Hou, Chence Shi, Xin Liu, Zhi Yang, Jian Tang
Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models: (Andrew) Zhanke Zhou, Zhaocheng Zhu, Xuan Li, Mikhail Galkin, Xiao Feng, Sanmi Koyejo, Jian Tang, Bo Han
Why Less is More (Sometimes): A Theory of Data Curation: Elvis Dohmatob, Mohammad Pezeshki, Reyhane Askari Hemmat
La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching: Tomas Geffner, Kieran Didi, Zhonglin Cao, Danny Reidenbach, Zuobai Zhang, Christian Dallago, Emine Kucukbenli, Karsten Kreis, Arash Vahdat
Embedding-Based Context-Aware Reranker: Ye Yuan, Mohammad Amin Shabani, Siqi Liu
Scaling Laws and Symmetry, Evidence from Neural Force Fields: Nhat Khang Ngo, Siamak Ravanbakhsh
Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards: Faisal Mohamed, Catherine Ji, Benjamin Eysenbach, Glen Berseth
GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks: Hao Xu, Xiangru Jian, Xinjian Zhao, Wei Pang, Chao Zhang, Suyuchen Wang, Qixin ZHANG, Zhengyuan Dong, Joao Monteiro, Bang Liu, Qiuzhuang Sun, Tianshu Yu
Diffusion Alignment as Variataional Expectation-Maximization: Jaewoo Lee, Minsu Kim, Sanghyeok Choi, Inhyuck Song, Sujin Yun, Hyeongyu Kang, Woocheol Shin, Taeyoung Yun, Kiyoung Om, Jinkyoo Park
Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling: Jonas Ngnawe, Maxime Heuillet, Sabyasachi Sahoo, Yann Pequignot, Ola Ahmad, Audrey Durand, Frederic Precioso, Christian Gagné
Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation: Israfel Salazar, Manuel Fernández Burda, Shayekh Islam, Arshia Soltani Moakhar, Shivalika Singh, Fabian Farestam, Angelika Romanou, Danylo Boiko, Dipika Khullar, Mike Zhang, Dominik Krzemiński, Jekaterina Novikova, a Shimabucoro, Joseph Marvin Imperial, Rishabh Maheshwary, Sharad Duwal, Alfonso Amayuelas, Swati Rajwal, Jebish Purbey, Ahmed Ruby, Nicholas Popovič, Marek Suppa, Azmine Toushik Wasi, Ram Mohan Rao Kadiyala, Olga Tsymboi, Maksim Kostritsya, Bardia moakhar, Gabriel da Costa Merlin, Otávio Coletti, Maral Jabbarishiviari, MOHAMMADAMIN FARAHANIFARD, Silvia Fernandez, María Grandury, Dmitry Abulkhanov, Drishti Sharma, Andre Guarnier De Mitri, Leticia Marchezi, Setayesh Heydari, Johan S Obando Ceron, Nazar Kohut, Beyza Ermis, Desmond Elliott, Enzo Ferrante, Sara Hooker, Marzieh Fadaee
Hierarchical Value-Decomposed Offline Reinforcement Learning for Whole-Body Control: Zhilong Zhang, Yunpeng Mei, Xinghao Du, Hongjie Cao, Haonan Wang, Pengyuan Min, Chenyu Wang, Pengfei Chen, Chenbo Xin, Yijie Wang, Wenyu Luo, Yihao Sun, Yidi Wang, Lei Yuan, Gang Wang, Yang Yu
Bridging Explainability and Embeddings: BEE Aware of Spuriousness: Cristian D. Paduraru, Antonio Barbalau, Radu Filipescu, Andrei Nicolicioiu, Elena Burceanu
When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training: Sanxing Chen, Xiaoyin Chen, Yukun Huang, Roy Xie, Bhuwan Dhingra
Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs: Yan Scholten, Sophie Xhonneux, Leo Schwinn, Stephan Günnemann
SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration: Kaustubh Mani, Yann Pequignot, Vincent Mai, Liam Paull
ADM-v2: Pursuing Full-Horizon Roll-out in Dynamics Models for Offline Policy Learning and Evaluation: Haoxin Lin, Siyuan Xiao, Yi-Chen Li, Zhilong Zhang, Yihao Sun, Chengxing Jia, Yang Yu
Planner Aware Path Learning in Diffusion Language Models Training: Zhangzhi Peng, Zachary Bezemek, Jarrid Rector-Brooks, Shuibai Zhang, Michael Bronstein, Anru Zhang, Joey Bose, Alexander Tong
On The Surprising Effectiveness of a Single Global Merging in Decentralized Learning: Tongtian Zhu, Tianyu Zhang, Mingze Wang, Zhanpeng Zhou, Can Wang
h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Network: Yanru Qu, Yijie Zhang, Wenjuan Tan, Xiangzhe Kong, Xiangxin Zhou, Chaoran Cheng, Mathieu Blanchette, Jiaxuan You, Ge Liu
RAEE: A Robust Retrieval-Augmented Early Exit Framework for Efficient Inference: LIANMING HUANG, Shangyu Wu, Yufei CUI, Ying Xiong, Haibo Hu, Xue Liu, Tei-Wei Kuo, Nan Guan, Chun Jason Xue
DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging: Kotaro Yoshida, Yuji Naraki, Takafumi Horie, Ryotaro Shimizu, Ioannis Mitliagkas, Hiroki Naganuma
On Fairness of Task Arithmetic: The Role of Task Vectors: Laura Gomezjurado Gonzalez , Hiroki Naganuma, Kotaro Yoshida, Takafumi Horie, Yuji Naraki, Ryotaro Shimizu
A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond: Nikos Tsikouras, Yorgos Pantis, Ioannis Mitliagkas, Christos Tzamos
Building spatial world models from sparse transitional episodic memories: Zizhan He, Maxime Daigle, Pouya Bashivan
A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic: Joseph Cotnareanu, Didier Chételat, Yingxue Zhang, Mark Coates
Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation: Egor Cherepanov, Nikita Kachaev, Artem Zholus, Alexey Kovalev, Aleksandr Panov
Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations: Zichao Li, Gang Wu, Zichao Wang, Vlad Morariu, Ruiyi Zhang, Wanrong Zhu, Ryan Rossi, Jihyung Kil
Relative Entropy Pathwise Policy Optimization: Claas Voelcker, Axel Brunnbauer, Marcel Hussing, Michal Nauman, Pieter Abbeel, Radu Grosu, Eric Eaton, Amir-massoud Farahmand, Igor Gilitschenski
Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds: Oscar Davis, Nicholas Boffi, Michael Albergo, Michael Bronstein, Joey Bose
Setting the Record Straight on Transformer Oversmoothing: Gbètondji J-S Dovonon, Michael Bronstein, Matt J. Kusner
Workshops
The Illusion of Superposition in Latent CoT via Soft Thinking: Michael Rizvi-Martel, Marius Mosbach
A Geometric Perspective on Zero-Shot Variant Effect Prediction Across the Central Dogma: César Miguel Valdez Córdova, Aaron Wenteler
Is Depth Heterogeneity a Barrier to Model Merging? Nour Shaheen, Sarath Chandar, Boris Knyazev, Ekaterina Lobacheva
LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents: Davide Baldelli, Ali Parviz, Amal Zouaq, Sarath Chandar
What Lies Beneath the Curve? Scaling Laws in the Presence of Exact Posteriors: Arian Khorasani, Nathaniel Chen, Yug D Oswal, Akshat Santhana Gopalan, Egemen Kolemen, Ravid Shwartz-Ziv
Value Drifts: Tracing Value Alignment During LLM Post-Training: Mehar Bhatia, Shravan Nayak, Gaurav Kamath, Marius Mosbach, Karolina Stanczak, Vered Shwartz and Siva Reddy
Multimodal Manifold Learning for Clonally Constrained Trajectory Inference: Irene Bonafonte Pardàs, Myriam Lizotte, Guy Wolf, Benjamin Schubert
A Comparative Study of Molecular Dynamics Approaches for Simulating Ionic Conductivity in Solid Lithium Electrolytes: Dounia Shaaban Kabakibo, Félix Therrien, Yoshua Bengio, Michel Côté, Hongyu Guo, Homin Shin and Alex Hernández-García
Latent Action Reparameterization for Efficient Agent Inference: Qingwen Zeng, Wenhao Huang, Zerui Xu, Zijie Guo, Yu Sun, Cheng Yang, Siru Ouyang, Jiri Gesi, Fang Wu, Jiayi Zhang, Bang Liu, Chenglin Wu, Xiangru Tang
Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks: Abhranil Chandra, Ayush Agrawal, Arian Hosseini, Sebastian Fischmeister, Rishabh Agarwal, Navin Goyal, Aaron Courville
The Geometry of Spectral Gradient Descent: Layerwise Criteria for SignSGD vs SpecSGD: Hiroki Naganuma, Laura Gomezjurado Gonzalez, Mahdi Ghaznavi, Ioannis Mitliagkas
Beyond Reward Maximization: Evaluating the Diversity of Trajectories in Reinforcement Learning with Temporal Vendi Score: Stanic Tom, Marco Jiralerspong, Zhang Xiaofeng, Danilo Vucetic, Gauthier Gidel
Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms: Linh Le, David Williams-King, Mohamed Amine Merzouk, Aton Kamanda, Adam Oberman
Deriving Hyperparameter Scaling Laws via Modern Optimization Theory: Egor Shulgin, Dimitri von Rütte, Tianyue H. Zhang, Niccolò Ajroldi, Bernhard Schölkopf, Antonio Orvieto
The Role of Data in Model Merging: Gaurav Iyer, Ekaterina Lobacheva
Alien Science: Sampling Coherent but Cognitively Unavailable Research Directions from Idea Atoms: Alejandro H. Artiles, Martin Weiss, Levin Brinkmann, Anirudh Goyal, Nasim Rahaman
Continuous RTS-PnO: Constraint-Aware Training for Robust Rolling-Horizon Budget Allocation: Rassul Magauin, Fuyuan Lyu, Lu Han, Xue Liu
From Large-Scale Winds to Urban Decision Making: A Cross-Scale Framework for Wind-Aware UAV Navigation: Shaoxiang Qin, Fuyuan Lyu, Di Zhou, Xue Liu, Xiongye Xiao, Anima Anandkumar, Liangzhu Wang
Towards Reasoning Reuse: A New Paradigm in Model Collaboration: Zhengxi Li, Fuyuan Lyu, Qiyuan Zhang, Ye Yuan, Haolun Wu, Xue Liu
The implicated scientist: on the role of AI researchers in the development of weapons systems: Alexandra Volokhova, Alex Hernandez-Garcia
Monitoring access to piped water and sanitation infrastructure in africa at disaggregated scales using satellite imagery and selfsupervised learning: Othmane Echchabi
Autoregressive Boltzmann Generators: Danyal Rehman, Charlie B. Tan, Yoshua Bengio, Joey Bose, Alexander Tong
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings: Shiva Krishna Reddy Malay, Shravan Nayak, Aman Tiwari, Jishnu Sethumadhavan Nair, Sathwik Tejaswi Madhusudhan, Sagar Davasam, Srinivas Sunkara, Sai Rajeswar
CUA-Suite: Expert Trajectories and Pixel-Precise Grounding for Computer-use Agents: Xiangru Jian, Shravan Nayak, Kevin Qinghong Lin, Aarash Feizi, Kaixin Li, Patrice Bechard, Spandana Gella, Sai Rajeswar
Soft Mellowmax Monte Carlo Planning: Danilo Vucetic, Marco Jiralerspong, Gauthier Gidel
Overcoming the Modality Gap in Context-Aided Forecasting: Vincent Zhihao Zheng, Étienne Marcotte, Arjun Ashok, Andrew Robert Williams, Lijun Sun, Alexandre Drouin, Valentina Zantedeschi
Objective Misalignment in LLM-based Multi Agent Social Deception Game: Marylou Fauchard, Florian Carichon, Margarida Carvalho, Golnoosh Farnadi
Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs: Edie Pearman, Sophia Osborne, Mira Kandlikar-Bloch, Mina Arzaghi, Florian Carichon, Golnoosh Farnadi
Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization: Yonghan Yang, Ye Yuan, Zipeng Sun, Linfeng Du, Bowei He, Haolun Wu, Can Chen, Xue Liu
Towards Reasoning Reuse: A New Paradigm in Model Collaboration: Zhengxi Li, Fuyuan Lyu, Qiyuan Zhang, Ye Yuan, Haolun Wu, Xue Liu
LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs: Benno Krojer, Shravan Nayak, Oscar Mañas, Vaibhav Adlakha, Desmond Elliott, Siva Reddy, Marius Mosbach
Understanding Scaling Laws With Token-Level Analysis :Arkil Patel, Marius Mosbach, Siva Reddy, Dzmitry Bahdanau
On the Simplicity-Similarity Tradeoff of LoRA and Full Fine-Tuning: Jerome Emery, Darshan Patil, François Leduc-Primeau, Sarath Chandar, Ekaterina Lobacheva
Shared Gradient Discovery and Superposition: Learning Dynamics of Generalization in LLMs: Andrei Mircea, Ildus Sadrtdinov, Irina Rish, Ekaterina Lobacheva
Loss Smoothing for Continual Adaptation: Darshan Patil, Ekaterina Lobacheva, Razvan Pascanu, Sarath Chandar
The Invisibility Hypothesis: Promises of AGI and the Future of the Global South: Leopoldo Julian Lechuga Lopez, Luis Lara
Adaptive Order Policies for Masked Diffusion: Mohsin Hasan, Jama Hussein Mohamud, Mirco Ravanelli, Yoshua Bengio
Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes: Aly M. Kassem, Thomas Jiralerspong, Negar Rostamzadeh, Golnoosh Farnadi
Understanding Repesentation Gaps Across Scales In Tropical Tree Species Classification from Drone Imagery: Sulagna Saha, Arthur Ouaknine, Etienne Laliberte, Carol Altimas, Evan M. Gora, Adriane Esquivel Muelbert, Ian McGregor, Cesar Gutierrez, Vanessa Rubio, David Rolnick
VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations :Yupeng Xie, Zhiyang Zhang, Yifan Wu, Sirong Lu, Jiayi Zhang, Zhaoyang Yu, Jinlin Wang, Sirui Hong, Bang Liu, Chenglin Wu, Yuyu Luo
Privileged Information Distillation for Language Models: Emiliano Penaloza, Dheeraj Vattikonda, Nicolas Gontier,Alexandre Lacoste, Laurent Charlin, Massimo Caccia
Benchmarking Code Verification Strategies with LLMs-as-a-judge: Arnav Kumar Jain, Justin T Chiu, Tom Sherbrone, Matthias Galle
Emergent Reasoning via Recursive Latent Reinforcement Pretraining: Gopeshh Subbaraj, Istabrak Abbes, Artem Zholus, Matthew Riemer, Irina Rish, Sarath Chandar
AIF-GEN: Open-Source Platform and Synthetic Dataset Suite for Reinforcement Learning on Large Language Models: Shahrad Mohammadzadeh, Jacob Chmura, Ivan Anokhin, Jacob-Junqi Tian, Mandana Samiei, Taz Scott-Talib, Irina Rish, Doina Precup, Reihaneh Rabbany, Nishanth Anand
