Accepted Papers

Oral Papers (8 min presentation + poster)

1. 1. 1. 1. 1. 1. “Diffusion as Prior Construction: A Bayesian View of Communication in Multi-Agent POMDPs” Muhyun Byun, Eunae Lee, Jahun Oh, Seok Joo Doo, poster #2906A

               2. “When Thinking Hurts: Epistemic Signals in the Reasoning Chains of Visual Language Models” Mayank Singal, poster #2906B

               3. “On the Epistemic Uncertainty of Overparametrized Neural Networks” David Rügamer, poster #2907A

               4. “MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation” Ahanaf Hasan Ariq, poster #2907B

Spotlight Papers (5 min presentation + poster)

1. 1. 1. 1. 1. 5. “What Does Disagreement Mean? A Semantic Identifiability Frontier for Pairwise Preference Learning” Manoj Saravanan, Rohit Kumar Salla, Shrikar Reddy Kota, poster #2908A

               6. “Geometry-Aware Uncertainty Quantification via Conformal Prediction on Manifolds” Marzieh Amiri Shahbazi, Ali Baheri, poster #2908B

               7. “What Shapes Emergent Misalignment?” Yuchen Zhang, Anietta Weckauff, Diego Garcia-Olano, Maksym Andriushchenko, poster #2909A

               8. “Decomposing Epistemic Uncertainty for Causal Decision Making” Md Musfiqur Rahman, Ziwei Jiang, Hilaf Hasson, Murat Kocaoglu, poster #2909B

               9. “Task-Aware Calibration: Provably Optimal Decoding in LLMs” Tim Tomov, Dominik Fuchsgruber, Rajeev Verma, Stephan Günnemann, poster #2910A

               10. “Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy” Ishaan Kelkar, Nebras Alam, Vikram Kakaria, Kevin Zhu, Maheep Chaudhary, poster #2910B

               11. “Leveraging Class Similarity for Enhanced Conformal Prediction” Ariel Fargion, Lahav Dabah, Tom Tirer, poster #2911A

               12. “A Tale of Two Uncertainties: Global–Local Attribution for Conformal Prediction” Sangyeon Cho, Minyoung Cho, Jungsoo Kim, Sujeong Oh, Sanghack Lee, poster #2911B

               13. “Same Target, Different Basins: Hard vs. Soft Labels for Annotator Distributions” Mirerfan Gheibi, Gashin Ghazizadeh, poster #2912A

               14. “The Posterior-Prior Epistemic Gap: When World Model Imagination Fails to Carry Task-Relevant Signals” Jaerock Kwon, Elahe Delavari, Donghyun Kim, Haewoon Nam, poster #2912B

               15. “Robust Learning to Rank from Incomplete Rankings under Positional Censoring” Cristiano Migali, Gianmarco Genalti, Alberto Maria Metelli, Marco Mussi, poster #2913A

               16. “Epistemic Gatekeeper: Training-Free One-Shot Gating for Open-World Industrial Anomaly Detection” Geonwoo Kim, Hyeonjun Kim, Chaein Oh, Suk-Ju Kang, poster #2913B

               17. “Rethinking Uncertainty Evaluation in Large Language Models” Krish Matta, Atharv Naphade, Andy Zou, poster #2914A
                   
                   

Poster Papers (poster)

1. 1. 1. 1. 1. 18. “Ontological Closure and Structural Limits on Systemic AI” Maneth Perera, Poojak Patel, poster #2914B

               19. “When Uncertainty Isn't Enough: An Empirical Study of Self-Correction in Code Generation” Pranav Rakasi, Tinuade Adeleke, Arya Senthilkumar Palanivel, Maanas Lalwani, Arnav Srivastava, Sean Wu, Ruizhe Li, poster #2915A

               20. “Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?” Jean Rojas, Viraj Vilas Sawant, Nathan Allen, Nomgondalai Amgalanbaatar, Yannis Zongo, Kevin Zhu, Maheep Chaudhary, poster #2915B

               21. “Open-World Sequential Belief Revision with Dynamic Functional Experts” David Scott Lewis, poster #2916A

               22. “What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics” Sofiia Nikolenko, Michele Papucci, Mina Rezaei, Shireen Kudukkil Manchingal, poster #2916B

               23. “Why Limit the Residual Stream to Layers and Not Tokens? Persistent Memory for Continuous Latent Reasoning” Mujtaba Farhan, Kevin Zhu, Maheep Chaudhary, poster #2917A

               24. “MAND: Modality-Aware Novelty Detection for Open-World Egocentric Activity Recognition” Hyejeong Im, Wonseon Lim, Dae-Won Kim, poster #2917B

               25. “Space-sampled Value Decay: Forgetting Mechanisms for Non-stationary Deep Reinforcement Learning” Felix Störck, Fabian Hinder, Barbara Hammer, poster #3000A

               26. “Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors” Akira Okutomi, poster #3000B

               27. “When Prediction Is Not Enough: Identifying Hidden Structure under Partial Observation” Jeongjun Lee, Laura Mascarell, Lancelot Da Costa, Ukyo T. Tazawa, Sundong Kim, poster #3001A

               28. “Pipeline-Aware Split Conformal Prediction: A Single-Quantile Reduction for Joint Coverage Under Compositional Uncertainty” Varun Kotte, poster #3001B

               29. “Authority, Truth, and Citation Bias: A Large-Scale Multi-Domain Benchmark for Studying Epistemic Susceptibility in Large Language Models” Aryan Khurana, Aravind Ramana RN, Dhruv Kumar, poster #3002A

               30. “Conformal Steering of LLMs via Posterior Sampling” Nicolas Emmenegger, Theo X. Olausson, Armando Solar-Lezama, Chara Podimata, poster #3002B

               31. “Confidence Without Warrant: A Formal Theory of Epistemic Blind Spots in Learning Systems” Siddharth Karuturi, Kaustubh S. Bukkapatnam, Soham Batra, Mithil Shah, Tanush Ajay Shastry, Akshath Sharma, Laksh Patel, Aarav Lala, Neel N Shanbhag, Andrew Bae, poster #3003A

               32. “From Critic to Confidence: PPO for Language-Based Quantitative Prediction with Confidence Estimation” Mehak Preet Dhaliwal, Rasta Tadayon, Andong Hua, Haewon Jeong, Yao Qin, poster #3003B

               33. “How do Consonance Constructions Shape Conformal Credal Sets?” Chun Ho Chong, Kaizheng Wang, Michele Caprio, Siu Lun Chau, poster #3004A

               34. “The Mechanistic Invariance Test: Genomic Language Models Fail to Learn Positional Regulatory Logic” Bryan Cheng, Jasper Zhang, poster #3004B

               35. “When Symbolic Rules Cannot Find Their Own Triggers: An Epistemic Diagnosis of Predicate Grounding Collapse in Neuro-Symbolic Fraud Detection” Farjana Yesmin, Nusrat Shirmin, poster #3005A

               36. “Activation Probing for Uncertainty-Aware Tool Routing in Agentic LLMs” Bastien Zimmermann, Louis Hernandez, Clément Pierquin, Matthieu Boussard, poster #3005B

               37. “What Uncertainties Do We Need for Dynamical Systems?” Yusuf Sale, Christopher Bülte, Felix Czaja, Joshua Stiller, Eyke Hüllermeier, poster #3006A

               38. “Characterizing the Consistency of the Emergent Misalignment Persona” Anietta Weckauff, Yuchen Zhang, Maksym Andriushchenko, poster #3006B

               39. “Sharp Thresholds and Non-Gaussian Limits of Compositional Deep GPs” Mark Kozdoba, Shie Mannor, poster #3007A

               40. “Quantifying Subliminal Behavioral Transfer Ratios in Language Model Distillation” Uwe König, Hamza Kazmi, Ruizhe Li, Maheep Chaudhary, poster #3007B

               41. “Validation Windows: Epistemic Uncertainty Produced by the Solver in a Literature-Derived Bayesian Network” Deborah Vakas Duong, Igor Yi, poster #3008A

               42. “In-Context Learning for Latent Space Bayesian Optimization” Tuan A. Vu, Harri Lähdesmäki, Julien Martinelli, poster #3008B

               43. “Hybrid Adaptive Prediction Sets for Conformal Prediction” Soundouss Messoudi, Abdelhak Imoussaten, poster #3009A

               44. “When To Trust a Temporal Prior: Order-Aware Test-Time Adaptation with Likelihood-Ratio Abstention” Young Kyung Kim, Oded Schlesinger, Qiangqiang Wu, J. Matias Di Martino, Guillermo Sapiro, poster #3009B

               45. “LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data” Akshat Dasula, Prasanna Desikan, Jaideep Srivastava, poster #3010A

               46. “Stacking-Based Weighting for Large Language Bayes in M-Open Settings” Anant Bhide, Akarsh Gupta, Edmond Cunningham, Justin Domke, poster #3010B

               47. “Indirect Query Bayesian Optimization with Integrated Feedback” Mengyan Zhang, Shahine Bouabid, Cheng Soon Ong, Seth Flaxman, Dino Sejdinovic, poster #3011A

               48. “Mechanistic Signatures of Recursive Reasoning in a Minimal Shared-Update Transformer Stack” Yi Liu, Ran Zhu, Jialiang An, Yunhan Jiang, Meng Lu, poster #3011B

               49. “Refusal Behavior Beyond English: A Multilingual Study of Representation Directions” Adith N Reganti, Malhar Udmale, Hardik Sharma, Soham Wasmatkar, Vaibhav Shukla, Bagesh Kumar, poster #3012A

               50. “Calibrated Surrogate Losses for Adversarial Classification With a Reject Option” Boris Ndjia Njike, Andriy Balinskyy, Waleed Mustafa, Puyu Wang, Antoine Ledent, Sophie Fellenz, Marius Kloft, poster #3012B

               51. “Green-Edge-Cloud: Routing without Routers via Confidence Calibration” Gao Yunzhe, Zijian Feng, Kezhi Mao, poster #3013A

               52. “Calibration of Structured Ignorance Certificates for Epistemic Diagnosis of Unknown Unknowns in Reasoning Models” Subramanyam Sahoo, poster #3013B

               53. “Learnability-Aware Replay for Mathematical Reasoning: Epistemic Uncertainty as a Guide for Experience Selection” Om Shastri, poster #3014A

               54. “Beyond a Single Signal: SPECTRE-G2 – A Unified Multi-Expert Anomaly Detector for Unknown Unknowns” Rahul D Ray, poster #3014B

               55. “Decoupled Conformal Optimisation: Efficient Prediction Sets via Independent Tuning and Calibration” Fanyi Wu, Lihua Niu, Michele Caprio, poster #3015A

               56. “Probabilistic Chain-of-Thought: Sequential Bayesian Inference over Latent Reasoning Correctness” Suriya Dev Saravanakumar, Ezra Matiwos Wesenie, Kishore Nuthalapati, Laksh Patel, poster #3015B

               57. “Modeling Incomparability: A New Rationality Paradigm for Preference-Based Reinforcement Learning” Simone Drago, Marco Mussi, Leonardo Bianconi, Alberto Maria Metelli, poster #3016A

               58. “I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation” Haotian Zong, Binze Li, Yufei Long, Sinyin Chang, Jialong Wu, Gillian K Hadfield, poster #3016B

               59. “Split Conformal Prediction with Label-Shift-Adjusted Bayesian Scores” Hyeonsu Lee, Erkhembayar Jadamba, Juyeon Kim, Seungjin Choi, Hyunjin Shin, poster #3017A

               60. “ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience” Jia Luo, poster #3017B

               61. “ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning” Nearchos Potamitis, Lars Henning Klein, Akhil Arora, poster #3100A

               62. “Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning” Shireen Kudukkil Manchingal, Abhey Kalia, Fernanda Gonçalves Abrantes, Shebin Rawther, poster #3102B 

               63. “Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training” Vin Bhaskara, Haicheng Wang, poster #3101A

               64. “MissFlow: Flow Matching for Uncertainty-Quantified Imputation of Missing Tabular Data” Yonghyun Kwon, Sunil Hwang, Joonyoung Jeong, poster #3102A

               65. “Stochastic Sampling is Epistemically Shallow: The Dimensionality Gap Between Temperature Variation and Model Diversity in LLMs” Izhar Ali, poster #3103A

               66. “Exposure Bias as Epistemic Underidentification in Recursive Forecasting” Riku Green, Zahraa S. Abdallah, Telmo M Silva Filho, poster #3103B

               67. “ConfidenceBench: Evaluating Confidence Calibration in Large Language Models” Matthew Ffrench-Constant, Daniel Yang, Sanyam Kapoor, Xinmeng Huang, poster #3104A

               68. “Conformal Bayes under Label Shift: Post-Hoc Calibration vs. In-Training Adaptation” Seungjin Choi, poster #3104B

               69. “HalluHard: A Hard Multi-Turn Hallucination Benchmark” Dongyang Fan, Sébastien Delsad, Nicolas Flammarion, Maksym Andriushchenko, poster #3105A

               70. “How Effective are Vision Language Models at Adapting to Novel Artifacts?” Lance Ying, Séb Arnold, Fei Sha, Sjoerd van Steenkiste, poster #3105B

               71. “Mitigating Reward Hacking in RLHF via Advantage Sign Robustness” Shinnosuke Ono, Johannes Ackermann, Soichiro Nishimori, Takashi Ishida, Masashi Sugiyama, poster #3106A

               72. “Language-Anchored Prototype Learning for Unseen Compositions” Anna-Alina Bondarets, Taras Rumezhak, Volodymyr Karpiv, poster #3106B

               73. “Don't Guess What You Don't Know: Spectral Effective Rank as a Diagnostic for Conformal Safety Under Subsampling” Rahul D Ray, poster #3107A

               74. “Constrained Bayesian Experimental Design via Online Planning” Yujia Guo, Daolang Huang, Xinyu Zhang, Sammie Katt, Samuel Kaski, Ayush Bharti, poster #3107B

               75. “Mind the Gap: Recovering Quality in Interrupted LLM Generation Through Continuation Strategy Selection” Tarun Narayanan, Ajay Krishnan, poster #3108A

               76. “Safety Targeted Embedding Exploit via Refinement: LLM Safety as an Epistemic Coverage Problem” Joshua Adrian Cahyono, poster #3108B

               77. “Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Study” Kaizheng Wang, Yunjia Wang, Fabio Cuzzolin, David Moens, Hans Hallez, Siu Lun Chau, poster #3100B

               78. “Do Humans and Language Models Converge? A Dynamical Systems View of Human-AI Feedback and Co-evolution” Xuening Wu, Yanlan Kang, Qianya Xu, Kexuan Xie, Jiaqi Mi, Honggang Wang, Yubin Liu, Zeping Chen, poster #3109A

               79. “The Shape of Reasoning: Topological Analysis of Reasoning Traces in Large Language Models” Xue Wen Tan, Galen Lee, Nathaniel Tan, Stanley Kok, poster #3109B