Tracked topic
…Congratulations on this release — the focus on faithful, context-grounded QA with calibrated abstention and citation-anchored reasoning traces is really nice work, and getting 0.6B/1.7B models to match…
…Teacher-probability scaling then uses the teacher's confidence as a lightweight factor to further calibrate the strength of the gated supervision. A key empirical finding is that neither component alone improves…
…PIPE-Cypher combines schema profiling , reverse-query grounding , constrained generation , deterministic Cypher governance , execution validation , redaction , diversity controls , and a calibrated local LLM judge . Using local Qwen3.5-9B generation and judging…
…We further use functional conformal prediction (FCP) to calibrate detection thresholds adaptively. We evaluate Foresight with state-of-the-art vision-language-action policies in simulation on LIBERO-Long, ManiSkill-Long, and…
…Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration (2026) PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding (2026) Domino: Decoupling Causal Modeling from Autoregressive Drafting in…
…Calibration Diagnostics for Pseudo-Labelled Regression (2026) Martingale-Consistent Self-Supervised Learning (2026) Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judges (2026) The Partial Testimony of Logs: Evaluation of…
…a dynamic program or graph traversal, compiled once, yields unboundedly many calibrated instances. Others are intrinsically hard to solve but easy to verify, like planted subset-sum or constraint satisfaction. Both create…
…When is it Actually Worth Expanding a Speculative Tree? (2026) Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference (2026) SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration (2026…
…We also propose a multi-metric evaluation framework that extends beyond spatial overlap to include probabilistic calibration and VI assessment. Evaluation of six state-of-the-art methods shows that strong global…
…missing values, outliers, and duplicates in the real-world data create a prior mismatch that degrades both accuracy and confidence calibration simultaneously. Correcting this mismatch requires sequential decisions over cleaning operators whose…