FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models

• URL: http://arxiv.org/abs/2606.06547v1
• Date: Thu, 04 Jun 2026 08:00:51 GMT
• Title: FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models
• Abstract summary: We propose a two-stage PTQ framework for dLLMs that prioritizes the protection of fragile frontier states without requiring end-to-end diffusion rollouts.<n>We show that FAIR-Calib consistently outperforms state-of-the-art baselines on LLaDA and Dream (W4A4), reducing frontier decision flips and suppressing post-commit mismatches across diverse benchmarks.
• Score: 50.86041384789834
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion Large Language Models (dLLMs) refine tokens iteratively but commit them irreversibly, leading to a "stability lag" where early decisions remain fragile even after being written. We reveal that Post-Training Quantization (PTQ) error easily flips these borderline decisions at the write frontier, which are then permanently locked in and amplified. To address this, we propose Frontier-Aware Instability-Reweighted Calibration (FAIR-Calib), a two-stage PTQ framework for dLLMs. Stage I probes a full-precision teacher to estimate a position prior that combines frontier hits and masked-stage reliability. Stage II performs off-policy, layer-wise calibration by minimizing a reweighted hidden-state MSE, effectively prioritizing the protection of fragile frontier states without requiring expensive end-to-end diffusion rollouts. We further theoretically justify our weighted objective as a surrogate for output KL divergence. Empirically, FAIR-Calib consistently outperforms state-of-the-art baselines on LLaDA and Dream (W4A4), significantly reducing frontier decision flips and suppressing post-commit mismatches across diverse benchmarks.

Related papers

• SCoCaT: Success Conditioned Constrained Reinforcement Learning for Spacecraft Docking [0.4619828919345114]
  We show that a minimal augmentation to off-the-shelf RL algorithms like PPO resolves this feasibility collapse''<n>We empirically demonstrate that adding a dense per-step success signal via an auxiliary value critic improves the task completion rate while maintaining safety-critical constraint compliance.
  arXiv  Detail & Related papers  (2026-09-05T12:43:41Z)
• Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning [14.631835952085263]
  We propose a token-level masking rule that aligns updates with a finite-horizon policy-improvement bound via two mechanisms.<n> CPPO enhances training stability and significantly improves reasoning accuracy across various model scales.
  arXiv  Detail & Related papers  (2026-06-09T15:09:29Z)
• PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization [20.910779784518798]
  Group Relative Policy Optimization (GRPO) has been emerging as a leading choice, but its reliance on sparse outcome rewards severely limits credit assignment across intermediate steps.<n>We propose a two-stage model with a frozen hidden-state probe estimating belief-consistency and a lightweight attention-based head correcting it toward grounded correctness.<n> Experimental results show that PAIR achieves the highest AUROC on contaminated trajectories while operating at negligible inference cost.
  arXiv  Detail & Related papers  (2026-05-18T05:39:30Z)
• Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models [65.89572755202245]
  Diffusion Language Models (DLMs) offer stronger global awareness and highly parallel generation.<n>Post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient.<n>We propose a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference.
  arXiv  Detail & Related papers  (2026-05-12T09:39:06Z)
• Amortized-Precision Quantization for Early-Exit Vision Transformers [14.001192614503807]
  We introduce Amortized-Precision Quantization (APQ), a utilization-aware formulation that accounts for layer-wise exposure to quantization noise.<n>We propose Mutual Adaptive Quantization with Early Exiting (MAQEE), a bi-level framework that jointly optimize exit thresholds and bit-widths under explicit risk control to improve inference stability.
  arXiv  Detail & Related papers  (2026-05-08T06:27:04Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• SLIME: Stabilized Likelihood Implicit Margin Enforcement for Preference Optimization [0.0]
  We introduce SLIME, a reference-free alignment objective designed to decouple preference learning from generation quality.<n>Our results demonstrate that SLIME achieves superior performance compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-02T17:46:06Z)
• LEC: Linear Expectation Constraints for False-Discovery Control in Selective Prediction and Routing Systems [95.35293543918762]
  Large language models (LLMs) often generate unreliable answers, while uncertainty methods fail to fully distinguish correct from incorrect predictions.<n>We address this issue through the lens of false discovery rate (FDR) control, ensuring that among all accepted predictions, the proportion of errors does not exceed a target risk level.<n>We propose LEC, which reinterprets selective prediction as a constrained decision problem by enforcing a Linear Expectation Constraint.
  arXiv  Detail & Related papers  (2025-12-01T11:27:09Z)
• Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering [52.69447404069251]
  Large vision-language models (VLMs) have improved embodied question answering (EQA) agents by providing strong semantic priors for open-vocabulary reasoning.<n>We propose Prune-Then-Plan, a framework that stabilizes exploration through step-level calibration.
  arXiv  Detail & Related papers  (2025-11-24T22:50:50Z)
• Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models [7.422627253922975]
  We introduce Certifiable Safe-RLHF, a cost model trained on a large-scale corpus to assign semantically grounded safety scores.<n>With an appropriately scaled penalty, feasibility of the safety constraints can be guaranteed, eliminating the need for dual-variable updates.<n> Empirical evaluation demonstrates that CS-RLHF outperforms state-of-the-art model responses rendering at-least 5 times efficient against nominal and jail-breaking prompts.
  arXiv  Detail & Related papers  (2025-10-03T21:24:41Z)
• PT$^2$-LLM: Post-Training Ternarization for Large Language Models [52.4629647715623]
  Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment.<n>We propose PT$2$-LLM, a post-training ternarization framework tailored for LLMs.<n>At its core is an Asymmetric Ternary Quantizer equipped with a two-stage refinement pipeline.
  arXiv  Detail & Related papers  (2025-09-27T03:01:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.