acceptodds: the papers of ICLR 2027
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]Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models▲233.33
[PDF]Hallucinated Heterogeneity: LLM Social Simulations Exaggerate Who Responds to Interventions▲233.33
[PDF]Den2MoEE: Reconstructing Dense LLMs into Expert-Specialized Mixture-of-Experts for Efficient Embedding Models▲1.7k3.33
[PDF]dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM Scale▲1.7k3.33
[PDF]Cross-Trajectory Value Composition for Offline Goal-Conditioned Reinforcement Learning▲1.7k3.33
[PDF]WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing▲233.33
[PDF]SIGHT: Compositional Skill Routing for Instance-Specific Rubric Generation across Heterogeneous Multimodal Tasks▲1.7k3.33
[PDF]Randomized Manifold Smoothing for Formal Robustness to Semantically Meaningful Perturbations▲233.33
[PDF]Arbitrary-Accuracy Neural Approximation with Optimal Neuron Count and Near-Optimal Bit Complexity▲1.7k3.33
[PDF]DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection▲1.7k3.33
1 If this project is interesting to you, reach out at [email protected].