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]How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines▼1.1k3.25
[PDF]What You Observe Determines How You Identify Causal Effects: Evaluating Causal Models across Observational Views▲4.8k3.25
[PDF]A Depth-Indexed Sample-Complexity Exchange Rate Between In-Context Learning and Low-Rank Fine-Tuning▼1.1k3.25
[PDF]WAM-Bench: A Closed-Loop Benchmark for Open-Ended Instruction Following in Autonomous Driving▲4.8k3.25
[PDF]Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning▼1.1k3.25
[PDF]FoveaTree: Information-Density Trees for Query-Guided Visual Token Pruning in Video Large Language Models▼1.1k3.25
[PDF]Stability Does Not Mirror Plasticity: A Module-Level View of Declarative and Procedural Learning in Transformers▲3273.25
[PDF]Equivariant Deep Learning in Direct-Product Space for Electronic-Structure Hamiltonian Prediction▲3273.25
[PDF]dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models▼1.1k3.25
[PDF]Object Count Generalization Is an Interface Problem: Warping a Frozen Skill Instead of Retraining It▼1.1k3.25
1 If this project is interesting to you, reach out at [email protected].