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
30 results for “keyword:"model inference"” in ICLR 2027. 7 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Beyond Accuracy: Prefix-Invariant Realizations of Low-Precision Fast Matrix Multiplication▲8072.80
[PDF]Co-Evolving Trees and Control Policies: Bridging Posterior Optimality and Online Efficiency in Speculative Decoding▼5.8k2.33
[PDF]QAttrib-MoE: Runtime-Controlled Attribution of Cross-Precision Trajectory Divergence in Mixture-of-Experts Inference▼5.3k1.33
[PDF]TMOT: Geometric Optimal Transport over Target Representations for Speculative Verification▼1361.33
[PDF]PRISM: Principal-Residual Activation Sparsity via Structure-Aware Budget Allocation for Efficient LLM Inference▼5.8k2.33
[PDF]SLMCoach: Context-Adaptive LM-Head Caching with Cross-Turn Reuse for Efficient Small Language Model Inference▲5.4k3.00
[PDF]BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding▼1.2k3.00
[PDF]AVSG: Accelerated Vectorized Sparse Gather for Efficient KV Cache Offload in Sparse-Attention LLM Serving▲9.2k2.67
[PDF]BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration▲3972.67
Withdrawn or desk rejected (7)
[PDF]ReTree: Budget-Efficient Tree Speculative Decoding via Path Guidance and Sibling RecoveryWithdrawn1.67
[PDF]Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure ModesWithdrawn
[PDF]FusionAgent: Joint Search over Fusion Boundaries and Kernel Implementations for Whole-Model InferenceWithdrawn
[PDF]TreeSpark: From Acceptance Scores to Useful Work in Conditional Speculative DecodingWithdrawn1.33