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
1,220 results for “keyword:"spe"” in ICLR 2027. 252 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]TrinityASR: An End-to-End Model for Long-Form Speech Recognition and Speaker Diarization▲422.75
[PDF]OSFAL: Orthogonal Cross-Spectral Feature Alignment and Layer-Localized Cross-View Learning for Any-Scenario Person Re-Identification▼363.67
[PDF]When Reading Is Not Verifying: Executable Audits Decompose Verification Failures in Vision–Language Models▲3.0k2.33
[PDF]Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?▲14k3.00
[PDF]JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting▲9.2k2.67
[PDF]LoadMatch: Balancing Memory and Compute Loads in Quantized Models using Speculative Decoding▼4.3k2.00
[PDF]Self-Supervised Variational Diffusion with Temporal Tucker Modeling for Hyperspectral Image Restoration▲3922.67
[PDF]CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents▼4.3k2.00
[PDF]PoseSpecGS: Pose-Aligned Multimodal Gaussian Splatting with Spectrum-Response Rendering▼5.8k2.33
[PDF]Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters▲5103.00
[PDF]What Makes a Good Full-Duplex SLM? A Systematic Study of Architecture, Objectives, and Data▲9.2k2.67
[PDF]SphGaS: Spherical Gaussian Splatting for RF Spectrum Synthesis under Varying Transmitter–Receiver Configurations▼5.8k2.33
[PDF]An Infinite Information Exponent that Gradient Descent Still Learns at the Optimal Rate: The Value Catalyst in Softmax Attention▼71.25
[PDF]Temporal Pooling Shapes Covariance Geometry and Readout Risk in Random Recurrent Networks▼1.2k1.67
[PDF]BURST: Generator-First Spike-Count Generation with Adaptive Dispersion for Cross-Day Neuroprosthesis Calibration▲5.4k3.00
[PDF]Normalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training▲13k2.33
[PDF]Speculative Pipeline Decoding: Higher-Accuracy Drafting with Hidden Latency via Pipeline Parallelism▲3922.67
[PDF]Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding▲3.0k2.33
Withdrawn or desk rejected (252)
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00
[PDF]When to Act, Not What to Act: Prospective Authorization for Tool-Using Language ModelsWithdrawn1.33