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]When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation▼1371.33
[PDF]SHADOW ANCHORING: GROUNDING HUMAN- INTERPRETABLE CONCEPTS IN TRANSFORMERS VIA SPARSE AUTOENCODERS▼1371.33
[PDF]WHAT IS ONE SEARCH OPERATION WORTH? EVALUATING ITS DOWNSTREAM VALUE IN AUTOMATIC AGENT DESIGN▼1371.33
[PDF]When Does a Neural Sampler Actually Need the Target Score? Isolating the Role of Langevin Parameterisation▼16k1.33
[PDF]When LLMs Bid Rationally, and When They Don't: A Traceable Capability Split in Sealed-Bid Auctions▼1371.33
[PDF]Same Artifact, Two Faces: Why Black-Box Lineage Fingerprints Look Both Robust and Fragile▼1371.33
[PDF]Beyond Average Risk: Diagnosis-Priority Robust Learning for Structured Radiology Report Generation▼1371.33
[PDF]Flow Matching in Hierarchical Residual Coordinates for Non-Stationary Probabilistic Forecasting▼1371.33
[PDF]DTSA: Dual-Timescale Stability and Adaptation for Robust Offline Reinforcement Learning with Spiking Neural Networks▼5.3k1.33
[PDF]Targeted Remasking: Token-to-Mask Refinement as Inference-Time Correction for Diffusion Language Models▼5.3k1.33
[PDF]Cross-Architecture Universal SAEs: A Shared Sparse Dictionary for Vision and Diffusion Transformers▼1371.33
[PDF]When the Label Space Shrinks: Task-Adaptive Depth Compression via Recomputed Gradient-Residual Sensitivity▼1371.33
[PDF]A Progressive Multi-Stage Multimodal Dataset and Benchmark for Real-World Chinese Emotion Recognition▼1371.33
[PDF]Neuron Sharing in Multi-Task Reinforcement Learning Policies Follows the Geometry of the Task Parameterization▼1371.33
[PDF]Fails Before Repair Is Not Enough: Auditing the Validity of Executable Repair Benchmarks.▼1371.33
[PDF]POSEIDON: Reinforcement Learning for Molecular Design with LLM-Guided Structural Feedback▼1371.33
[PDF]Beyond Image-Wide Color Shifts: Scene-Compatible Semantic-Region Triggers for Backdoor Attacks▼1371.33
[PDF]Rewriting Is Forgetting: Zero Rewrite Capture and Budgeted Reading for Long Horizon Agent Memory▼1371.33
1 If this project is interesting to you, reach out at [email protected].