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.
[PDF]From Noise to Diversity: Random Embedding Injection in LLM ReasoningHeejun Kim, Seungpil Lee, Jewon Yeom et al.4.67
[PDF]Predictive Geometry of Hidden Trajectories in TransformersTimur Mudarisov, Mikhail Burtsev, Tatiana Petrova et al.4.67
[PDF]Meta-Learning Preferences for Multilingual LLM AlignmentJiaying Lin, Seongho Son, Nam P Tran et al.4.67
[abs]DeFlow: Decoupling Behavior-Prior Modeling and Value Maximization for Offline Policy ExtractionZhancun Mu, Chi Zhang4.67
[abs]VoluCore: Spanning Teacher Representations with Volumetric Coresets for Data-Efficient LLM DistillationWang Xi, Yue Wang4.67
[abs]Talk Less, Work More: Communication-Efficient Decentralized Stochastic ApproximationTianyu Cao, Haixiang Sun, Yang Xu4.67
[abs]Federated Distributionally Robust Neural Combinatorial Optimization with Convergence GuaranteesRyunosuke Hamada, Daisuke Hatano, Yuichi Takano4.67
[abs]Query Lower Bounds for Approximating the Top Eigenvector of Asymmetric MatricesKun Chen, Zhihua Zhang4.67
[abs]Kernel Value Regression in Offline Reinforcement LearningJongyeon Lee, Jaehyoung Jeon, Kim Haneol et al.4.67
[abs]Sparse Updates Generalize Better Than Optimization: Stability Analysis for Randomized Subspace DescentYifei Liang, Yan Sun, Yifei Cheng et al.4.67
[abs]Hyperbolic Language Models: From Zipf to Compute-Optimal ScalingJinrui Lin, Menglin Yang, Rex Ying4.67
[PDF]Phantom Transfer: Data Poisoning can Survive Data-Level DefencesAndrew Draganov, Tolga Hasan Dur, Anandmayi (Andi) Bhongade et al.4.67
[PDF]Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement LearningBoyang Li, Matthew Kim, Sylvia Herbert4.67
[PDF]Effective Multi-sensor Conditioning for Street-view Novel-view SynthesisZhengfei Kuang, Adam Sun, Liyuan Zhu et al.4.67
[abs]Pacing Branch Parallelism in LLM ServingSwapnil Gandhi, Siva Kumar Sastry Hari, Bill Dally et al.4.67
[PDF]Optimizing Social Utility in Sequential ExperimentsAnder Artola Velasco, Stratis Tsirtsis, Manuel Rodriguez4.67
[abs]LLM Rheology: Auditing Refusal Geometry in Aligned Language Modelsziyang zhao, Junlang Tian4.67
[PDF]Bayesian Decision Making around ExpertsDaniel Jarne Ornia, Joel Dyer, Nicholas Bishop et al.4.67
[PDF]Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential PrivacyKeqin Chen, Jie Bian, Yulian Wu et al.4.67
[PDF]Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General DiscountingMehrdad Moghimi, Anthony Coache, Hyejin Ku4.67
[abs]SAVeR: Reasoning-based Safety Alignment for Large Reasoning Models via Verifiable RewardsYichen Sun, LIN JIANAN, Linbo Jiang et al.4.67
[abs]Spherical Bayesian Experimental Design for Active View Selection in 3D Gaussian SplattingYan Song, Yunfei Guo, Guyeli Yang et al.4.67
[abs]SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised LearningJongann Lee, Sun Woo Park, Yun Young Choi4.67
[PDF]AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control TokensTung-Ling Li, Yuhao Wu, Hongliang Liu4.67
[abs]Compressing Collections of Trees with Decision EquivalenceHayden McTavish, Jon Donnelly, Margo Seltzer et al.4.67
[abs]Ripple in Still Water: Zero-Shot Clustering in Heterogeneous Federated Learning with Wavelet Scattering TransformAlessandro Licciardi4.67
[abs]Toward the Goldilocks Blind Compression of Quantum StatesHyunho Cha, Chae-Yeun Park, Jungwoo Lee4.67
[PDF]Emergent Low-Rank Training Dynamics in MLPs with Smooth ActivationsAlec Xu, Can Yaras, Matthew Asato et al.4.67
[PDF]Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry TransformerYipu Zhang, Jintao Cheng, Weilun Feng et al.4.67
[abs]C3: Long-Horizon Character Consistency via Causal-Continuous State Dynamics and Memory RewritingMinghao Chen4.67
[abs]Certified but Private: Scalable Zero-Knowledge Proofs for the Formal Verification of Neural NetworksYouwei Zhong, Ben Merbaum, Timos Antonopoulos et al.4.67
[abs]Compute Allocation Under Model-Provider CompetitionTori Qiu, Meena Jagadeesan, Benjamin Laufer et al.4.67
[abs]Conflict-Aware Logit Adapters for Utility-Preserving Anti-DistillationQuoc P Dao, Binh Anh Nguyen, Linh Ngo et al.4.67
[abs]Capricorn: Highly Efficient and Secure Mixture of Experts Inference FrameworkLushan Song, Xiaojian Liang, Shishuai Du et al.4.67
[PDF]Federated Concept-Based Models: Interpretable models with distributed supervisionDario Fenoglio, Arianna Casanova Flores, Francesco De Santis et al.4.67
[PDF]Communication-Efficient LLM Adaptation over Decentralized GPU MeshesSameera Ramasinghe, Shamane Siriwardhana, Thalaiyasingam Ajanthan et al.4.67
[PDF]Effective Context in Transformers: An Analysis of Fragmentation and TokenizationAmirmehdi Jafari Fesharaki, Mohammadamin Rami, Aslan Tchamkerten4.67
[PDF]The Price of Locality: Why Forward-Forward Underperforms Backpropagation?Zhaoxian Wu, Haichuan Liu, Tianyi Chen4.67
[abs]When Form Changes but Logic Doesn’t: Building Logic-invariant LLMs through StructuresXuyuan Liu, Xinshuai Dong, Elynn Chen et al.4.67
[abs]Two-Sided Learning in Matching Markets with InterviewsAmirmahdi Mirfakhar, Xuchuang Wang, Mengfan Xu et al.4.67
[abs]Policy-DRIFT: Dynamic Reward-Informed Flow Trajectory SteeringAtharva Mahajan, Abhijeet Vishwasrao, Yuning Wang et al.4.67
1 If this project is interesting to you, reach out at [email protected].