NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of NeurIPS 2026
Abstract
The safe for work edition of acceptodds: the submissions, without the markets. Search them, browse them on a map laid out by what they are about, follow the ones you care about, keep reading lists with your group, and get recommendations from what you read. There are no odds, no bets and no reputation here. acceptodds is not affiliated with any organisation or institution. acceptodds is an open source project, open to contributions, at github.com/PotentialHedge/acceptodds-sfw.1 Follow for updates on X.
[abs]SLIC: Reinforcement Fine-Tuning Small LMs for Multi-Turn Analog Circuit OptimizationYan Xu, Zhengqi Gao, Ching-Yun Ko et al.3.75
[abs]Efficient and Accurate Zero Shot Generation of Symmetric Protein ComplexesRory Gao, Yuanzhou Chen, Prajit Rajkumar et al.3.75
[PDF]Tool Verification for Test-Time Reinforcement LearningRuotong Liao, Nikolai Röhrich, Xiaohan Wang et al.3.75
[PDF]Unveiling the Value of Motion for Cinematic Camera TrajectoriesZiqi Zhou, Yujian Yuan, Laura Sevilla-Lara3.75
[PDF]PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage ReshapingQiming Li, Tianlun Li, Xiaolong Cheng et al.3.75
[PDF]Can Model Merging Improve Aggregation in DiLoCo?Stefan Horoi, Benjamin Thérien, Guy Wolf et al.3.75
[abs]Dynamics-Aware Sparse Attention for Efficient Autoregressive Video DiffusionYuanyu He, Zhuokun Chen, Yefei He et al.3.75
[PDF]RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit RepresentationsYanhao Ge, Shanyan Guan, Weihao Wang et al.3.75
[PDF]Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT DistillationZhixuan Liu, Zhichen Dong, Yuyu Fan et al.3.75
[abs]One-Time Soft Alignment Enables Resilient Learning without Weight TransportJeonghwan Cheon, Jaehyuk Bae, Se-Bum Paik3.75
[PDF]Reinforcement Learning from Rich Feedback with Distributional DAggerRishabh Agrawal, Jacob Fein-Ashley, Paria Rashidinejad3.75
[PDF]Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region MethodsSaksham Kiroriwal, Julius Pfrommer, Jürgen Beyerer3.75
[abs]EnerGNN: Learning Optimization-Compatible Energy Functions for Exact Constrained Combinatorial InferenceNiki Triantafyllou, Maria Papathanasiou3.75
[abs]CompJudge: Fine-Grained Comparative Evaluation using Multimodal LLM for Subject-Driven GenerationNam Hyeon-Woo, Wenbin Ouyang, Ciprian A Corneanu3.75
[abs]Learning Transferable Cross-Day Representations for Few-Shot Neural DecodingYue Chen, Menghan Li, Tatsuo S Okubo3.75
[abs]On-Policy Distillation with Open Property-Equivalence Reward for LLM-Based NL-to-SVA GenerationQingyun Zou, Yingze Li, Tianen Liu et al.3.75
[abs]MMCompass: Diagnosing Position Bias in Generative Multimodal Reward ModelsHongbo Zhao, Mingkun Yang, Yantao Liu et al.3.75
[PDF]SIEVES: Selective Prediction Generalizes through Visual Evidence ScoringHector G. Rodriguez, Marcus Rohrbach3.75
[abs]ToS: Tree-of-Skill Reinforcement Learning driven by Behavior Tree for Long-Horizon ManipulationXinglin Chen, Yishuai Cai, Yunxin Mao et al.3.75
[PDF]Learn from your own latents and not from tokens: A sample-complexity theoryDaniel Korchinski, Alessandro Favero, Matthieu Wyart3.75
[abs]Safe-Fair MACPO: Burden-Fair Constrained Policy Optimization for Safe Multi-Agent Reinforcement LearningAnkita Kushwaha, KIRAN RAVISH, Preeti et al.3.75
[PDF]CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMsShaobo Wang, Yongliang Miao, YuanCheng Liu et al.3.75
[abs]Multiclass Classification with Rare Useful Features: Fundamental Limits and the Optimality of Diversity Pursuit Higher CriticismGabriel Moryoussef, Alon Kipnis3.75
[abs]Face Deepfake-aware Recovery via Semantic-driven Facial Representation-based WatermarkingYuan-Chih Chen, Chun-Shien Lu3.75
[PDF]Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse AutoencodersChungpa Lee, Jihoon Kwon, Kyle Min et al.3.75
[PDF]SLIDERS: Systematic Reviews via Automated Evidence Synthesis and ReconciliationHarshit Joshi, Priyank Shethia, Jadelynn Dao et al.3.75
[PDF]Differencing the Diffusion Trajectory toward Uncertain Components for Time Series ForecastingChen Su, Yuanhe Tian, Yan Song3.75
[abs]On the fundamentals of gradient-based SAT solversNikolaos Karalias, Sakari Peltonen, Nikita Kostin et al.3.75
[PDF]Towards Mitigating Deceptive Safety Alignment in Large Reasoning ModelsXiangyu Zhou, Saleh Z Zade, Rafi Ibn Sultan et al.3.75
[PDF]Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous AgentsPaul Mangold, Eloïse Berthier, Eric Moulines3.75
[abs]Grouped Adaptive Head Mixing for Personalized Multi-Task Federated Reinforcement LearningYiran Pang, Zhen Ni, Dimitris Pados et al.3.75
[abs]User Embeddings are Superpositions of Interpretable Behavioral ModesJonathan Kozaczuk, Zheng Dong, Noyan Evirgen et al.3.75
[PDF]RADAR: Relative Angular Divergence Across RepresentationsXavier Cadet, Mateusz Nowak, Peter Chin3.75
[abs]Decision-Focused Learning in MDPs: An Occupancy Measure ApproachZihao Zhao, Ashwath K Karunakaram, Ali Eshragh et al.3.75
[PDF]Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law ExtrapolationJoshua Shay Kricheli, Alexander L. Reid, Soumajyoti Sarkar et al.3.75
[abs]Align as You Couple: Learning Spatial Resolved Inference from H&E Images with Mollified Flow MatchingRongchao Zhang, Guangyuan Dong, Siheng Wang et al.3.75
[PDF]Multi-Part Object Representations via Graph Structures and Co-Part DiscoveryAlex Foo, Wynne Hsu, Mong-Li Lee3.75
[PDF]How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard RobustnessPolina Gordienko, Georg Schollmeyer, Frauke Kreuter et al.3.75
[PDF]Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD GeneralizationLeonel Aguilar, Jan Nagler, Christoph Hoelscher et al.3.75
[abs]Replay-buffer engineering for noise-robust quantum circuit optimizationAkash Kundu, Sebastian Feld3.75
[abs]Uncertainty Quantification of Least Squares Estimator for Generalized Orthogonal Procrustes ProblemsShenghan Luo3.75
[PDF]Towards more general control of diffusion models using Jeffrey GuidanceRaphaël Razafindralambo, Rémy Sun, Frederic Precioso et al.3.75
[PDF]Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizerAratrika Mustafi, Soumya Mukherjee, Bharath Sriperumbudur3.75
[abs]Why Decoding Sharpens Without Resolving: Lock-in and Confusion in Autoregressive ReasoningNan Zhang, Heng Xu3.75
[abs]Compact Representations of Impact-Based Fair-Ranking PoliciesYuki Uehara, Naoki Nishimura, Noriyoshi Sukegawa et al.3.75
[abs]Local Manifold Identification with Latent Linear Models and OT FlowsSherman Khoo, Song Liu, Mark Beaumont3.75
1 If this project is interesting to you, reach out at [email protected].