NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
1,051 results for “keyword:"control"” in ICLR 2027. 300 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Does a Neural Sampler Actually Need the Target Score? Isolating the Role of Langevin Parameterisation▼16k1.33
[PDF]LOGIT-PATH TRACING: EXACT GREEDY DECODING PARTITIONS OF LANGUAGE MODELS UNDER AFFINE LOGIT CONTROLS▼4.3k2.00
[PDF]DPR: From High-Entropy Tokens to Learning Claims — Matched Evaluation for Token-Selective LLM Reinforcement Learning▼1361.33
[PDF]Measuring Heterogeneous Adaptation: From Nominal Configuration to Intervention Dependence▲11.00
[PDF]LOONA: Linearized Objectives over Noise Atoms for Controllable Zero-Shot Diffusion Image Compression▲5103.00
[PDF]Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control▼5.8k2.33
[PDF]VQ-PACT: Learning Compositional Temporal Grammars for Text-Controlled Time Series Generation▲3.0k2.33
[PDF]From Trajectory Evidence to Control: Latent Control-State Inference for Long-Horizon Language Agents▼1.2k1.67
[PDF]Where the Examples Were: Local Loss Weighting Inherits the Spatial Layout of Scarce Supervision in Diffusion Models▼4.3k2.00
[PDF]Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation▲6.6k3.33
[PDF]DragPhysSVG: Bridging Vector Graphics and Particle Dynamics for User-Controlled Animation▲5103.00
Withdrawn or desk rejected (300)
[PDF]What a 3D Reconstruction Benchmark Can and Cannot Tell About Geometric Foundation ModelsWithdrawn2.00
[PDF]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00
[PDF]AcoustiGym: Physics-Based Acoustic Environment Generation for Robotic Policy EvaluationDesk rejected