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
470 results for “keyword:"kv"” in ICLR 2027. 87 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Harnessing Smoothness: Asymmetric Differential Linear Attention for Vision Transformers▲3952.67
[PDF]Where Does Attention Mass Live? A Matched-Budget Study of Query-Adaptive Attention Sparsification for Decoder LMs▼1361.33
[PDF]RIVET: Ragged Inference with Variable-Granularity Execution for Token-Tree Verification in Speculative Decoding▼1.2k1.67
[PDF]DynamicKV: Predictive and Reversible KV-Cache Precision Allocation for Agentic LLM Inference▲2.0k4.00
[PDF]HorizonKV: Three-State KV Cache Compression under a Shrinking Generation Horizon for Visual Autoregressive Models▲3952.67
[PDF]Read Depth and Broadcast Depth: What Sharing Keys and Values Across Layers Costs a Transformer▲3.0k2.33
[PDF]CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches▲5103.00
[PDF]SAFETYEDIT: Sparse Internal Targets with Prompt-Wide Control for LLM Jailbreak Backdoors▼4.5k2.67
[PDF]RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache▼1.2k3.00
[PDF]DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency▼5.8k2.33
[PDF]QSpar: Co-Designing Sparse Attention and Quantized Weights for Long-Context Self-Speculative Decoding▲5103.00
[PDF]TraSURE: Exploiting Cross-trajectory Recurrence to Accelerate Information-seeking RL Rollouts over Shared Corpora▼5.8k2.33
[PDF]When the Second GPU Helps: Topology-Aware Mode Selection for Narrow-Interconnect LLM Serving▼1.3k1.75
[PDF]When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression▼1.2k3.00
[PDF]Same Score, Different State: Post-Training Moves Pre-Answer Recoverability under KV Compression▼4.3k2.00
[PDF]LociNav: Pose-Indexed Visual Caching and Retrieval for Iterative Object-Goal Navigation▲5103.00
[PDF]-Omni: Reducing Structural and Precision Redundancy in Omni-LLMs for Long-Form Generation▲5.4k3.00
Withdrawn or desk rejected (87)
[PDF]Certified Best-First Sparse Attention: Provable Early Termination via Admissible Block BoundsWithdrawn2.00
[PDF]Cross-Model KV Cache Construction in LLM Familiies: Residual-Stream Mapping Without Matched Head GeometryDesk rejected
[PDF]Trace Forcing: Anchor Tokens in the KV Cache for Training-Free Long Video GenerationWithdrawn2.00
[PDF]EviStream: Evidence-Aligned Audio-Visual Decisions over Partially Observable Video StreamsWithdrawn2.00