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
121 results for “keyword:"test time compute"” in ICLR 2027. 32 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Inference-Time Search in Discrete Diffusion Language Models, Guided by Internal-State Signals▼1.2k1.67
[PDF]Many Caches, Same Reasoning: Rethinking Importance Selection for Reasoning-Time KV Compression▼1.2k1.67
[PDF]Stopping Soft Reasoning before It Loops: From Impasse-Oriented Detection to Event-Level Intervention▼5.8k2.33
[PDF]Changing the Candidates, Not the Vote: A Repair Portfolio for Self-Consistency under a Per-Call Token Cap▼4.3k2.00
[PDF]Equal Exposure, Different Decisions: Reference Selection and Early Stopping for Pairwise LLM Judges▲14k2.50
[PDF]Regime-Dependent Inference-Time Compute Allocation for Agentic Systems: When Deeper Reasoning Wins▲3.0k2.33
[PDF]ReDraft: Your Verifier Is Secretly a Depth Supervisor for Recurrent Speculative Decoding▲5103.00
[PDF]Test-Time Compute in Chain-of-Thought and Looped Transformers: Simulation and Resource Trade-offs▼4.3k2.00
[PDF]Pareto Frontier of LLM Test-Time Compute: Adaptive Rollouts and Voting Under Token Budgets▲3.0k2.33
Withdrawn or desk rejected (32)
[PDF]How Faithful Is a Truncated Reasoning Trace? Measuring and Modeling Biased Feedback in Test-Time Compute AllocationWithdrawn1.60
[PDF]Which Questions Are Worth Thinking About? Cross-Developer Transfer of Thinking ValueWithdrawn1.75
[PDF]SpecRelay: Amortize or Avoid the Round Trip in Edge–Cloud Speculative DecodingDesk rejected2.00
[PDF]Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy OptimizationWithdrawn1.67
[PDF]Conflict Steering: Resolving Late-Layer Disagreement Repairs Non-Termination in Greedy ReasoningWithdrawn2.25
[PDF]The Sampling Ceiling: Why Test-Time Self-Consistency Saturates and an Oracle Rule for Allocating SamplesWithdrawn1.33