Continuous language diffusion works by entering high-margin decoder basins where frozen T5 embeddings recover 93-96% of native decisions and linear readouts reach 97.9% agreement, implying models should be evaluated as representation-decoder systems.
hub Canonical reference
A survey on parallel text generation: From parallel decoding to diffusion language models
Canonical reference. 100% of citing Pith papers cite this work as background.
13
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
QuantEvolver applies reinforcement fine-tuning to evolve an LLM policy for generating executable alpha factor expressions, yielding higher-quality and more complementary factors than prompt-based baselines on market benchmarks.
GPO-V jailbreaks dVLMs by globally optimizing probabilities in the denoising process to bypass refusal patterns, achieving stealthy and transferable attacks.
TAPER regulates LLM branch parallelism by admitting extra branches opportunistically when predicted externality fits slack, delivering 1.48-1.77x higher goodput than eager or fixed-cap baselines on Qwen3-32B while keeping over 95% SLO attainment.
Introduces the first benchmark for fine-grained failures in reinforcement fine-tuning of LLMs and an automatic management framework that detects, diagnoses, and remediates them.
E2E-REME outperforms nine LLMs in accuracy and efficiency for end-to-end microservice remediation by using experience-simulation reinforcement fine-tuning on a new benchmark called MicroRemed.
DMax uses On-Policy Uniform Training and Soft Parallel Decoding to enable aggressive parallelism in dLLMs, raising TPF on GSM8K from 2.04 to 5.47 and on MBPP from 2.71 to 5.86 while preserving accuracy.
d-TreeRPO uses tree rollouts for fine-grained verifiable rewards and time-scheduled self-distillation to reduce probability estimation gaps in diffusion LLMs, delivering substantial gains on Sudoku, Countdown, GSM8K, and Math500 benchmarks.
Masked diffusion models for graph-to-text generation unmask entities first and structural tokens last; supervised fine-tuning breaks this pattern, and a training-free lambda-scaled decoding fix recovers 9.4 BLEU-4 while Graph-LLaDA adds explicit graph encoding.
dMoE aggregates token expert distributions to block level in dLLMs, cutting unique experts from 69.5 to 14.6, memory by 76-80%, and latency by 1.14-1.66x while retaining 99.11% performance.
RCLAgent uses multi-agent recursion-of-thought with parallel reasoning on trace graphs to outperform prior methods in root cause localization accuracy and efficiency for microservice systems.
SpecBound achieves up to 2.33x wall-time speedup in LLM inference via adaptive bounded self-speculation and layer-wise confidence calibration while preserving exact output equivalence.
Saber improves both speed and accuracy of diffusion language models on code generation by dynamically adjusting unmasking steps and reverting low-confidence tokens via backtracking.
citing papers explorer
-
Continuous Language Diffusion as a Decoder-Interface Problem
Continuous language diffusion works by entering high-margin decoder basins where frozen T5 embeddings recover 93-96% of native decisions and linear readouts reach 97.9% agreement, implying models should be evaluated as representation-decoder systems.
-
From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery
QuantEvolver applies reinforcement fine-tuning to evolve an LLM policy for generating executable alpha factor expressions, yielding higher-quality and more complementary factors than prompt-based baselines on market benchmarks.
-
GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimization
GPO-V jailbreaks dVLMs by globally optimizing probabilities in the denoising process to bypass refusal patterns, achieving stealthy and transferable attacks.
-
Regulating Branch Parallelism in LLM Serving
TAPER regulates LLM branch parallelism by admitting extra branches opportunistically when predicted externality fits slack, delivering 1.48-1.77x higher goodput than eager or fixed-cap baselines on Qwen3-32B while keeping over 95% SLO attainment.
-
Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning
Introduces the first benchmark for fine-grained failures in reinforcement fine-tuning of LLMs and an automatic management framework that detects, diagnoses, and remediates them.
-
E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuning
E2E-REME outperforms nine LLMs in accuracy and efficiency for end-to-end microservice remediation by using experience-simulation reinforcement fine-tuning on a new benchmark called MicroRemed.
-
DMax: Aggressive Parallel Decoding for dLLMs
DMax uses On-Policy Uniform Training and Soft Parallel Decoding to enable aggressive parallelism in dLLMs, raising TPF on GSM8K from 2.04 to 5.47 and on MBPP from 2.71 to 5.86 while preserving accuracy.
-
d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models
d-TreeRPO uses tree rollouts for fine-grained verifiable rewards and time-scheduled self-distillation to reduce probability estimation gaps in diffusion LLMs, delivering substantial gains on Sudoku, Countdown, GSM8K, and Math500 benchmarks.
-
What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Generation
Masked diffusion models for graph-to-text generation unmask entities first and structural tokens last; supervised fine-tuning breaks this pattern, and a training-free lambda-scaled decoding fix recovers 9.4 BLEU-4 while Graph-LLaDA adds explicit graph encoding.
-
dMoE: dLLMs with Learnable Block Experts
dMoE aggregates token expert distributions to block level in dLLMs, cutting unique experts from 69.5 to 14.6, memory by 76-80%, and latency by 1.14-1.66x while retaining 99.11% performance.
-
Towards In-Depth Root Cause Localization for Microservices with Multi-Agent Recursion-of-Thought
RCLAgent uses multi-agent recursion-of-thought with parallel reasoning on trace graphs to outperform prior methods in root cause localization accuracy and efficiency for microservice systems.
-
SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
SpecBound achieves up to 2.33x wall-time speedup in LLM inference via adaptive bounded self-speculation and layer-wise confidence calibration while preserving exact output equivalence.
-
Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model
Saber improves both speed and accuracy of diffusion language models on code generation by dynamically adjusting unmasking steps and reverting low-confidence tokens via backtracking.