PARAMΔ upcycles dense models to MoE for per-language experts and grafts post-training deltas to enable data-efficient language expansion while preserving original capabilities.
hub
Journal of Machine Learning Research , volume=
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
years
2026 13verdicts
UNVERDICTED 13representative citing papers
Polyphonia improves zero-shot stem-specific timbre transfer in polyphonic music by 15.5% target alignment via acoustic-informed attention calibration that uses probabilistic priors to set coarse boundaries.
LLMs copy biased analyst ratings in investment decisions but a new detection method encourages independent reasoning and can improve stock return predictions beyond human levels.
PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
Pragmatic reasoning in LLMs varies substantially by evaluation method and model family, with scalar diversity patterns appearing only in certain conditions rather than reflecting stable competence.
pFLAlign uses two gradient alignment mechanisms derived from PAC-Bayesian analysis to reduce variance in local training and distortion in aggregation, yielding state-of-the-art personalization in federated learning.
A formalized Minimal Cognitive Grid ranks computational models of analogy and metaphor by alignment with cognitive theories using Functional/Structural Ratio, Generality, and Performance Match dimensions.
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.
Fine-tuned 8B LLMs produce children's English reading stories with better difficulty control and safety than zero-shot GPT-4o and Llama 3.3 70B.
Conversational scenario modeling from user profiles and domain knowledge, combined with intent-keyword bridging, improves proactivity, fluency, and informativeness in target-guided proactive dialogue systems.
Reproducibility study diagnoses semantic drift in PO4ISR and introduces PO4ISR++ with reflexive prompting that restores performance with gains up to 54% on Games and 96% on Bundle.
citing papers explorer
-
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE
PARAMΔ upcycles dense models to MoE for per-language experts and grafts post-training deltas to enable data-efficient language expansion while preserving original capabilities.
-
Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration
Polyphonia improves zero-shot stem-specific timbre transfer in polyphonic music by 15.5% target alignment via acoustic-informed attention calibration that uses probabilistic priors to set coarse boundaries.
-
Fin-Bias: Comprehensive Evaluation for LLM Decision-Making under human bias in Finance Domain
LLMs copy biased analyst ratings in investment decisions but a new detection method encourages independent reasoning and can improve stock return predictions beyond human levels.
-
PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts
PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.
-
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
-
Evaluating Pragmatic Reasoning in Large Language Models: Evidence from Scalar Diversity
Pragmatic reasoning in LLMs varies substantially by evaluation method and model family, with scalar diversity patterns appearing only in certain conditions rather than reflecting stable competence.
-
Personalized Federated Learning for Gradient Alignment
pFLAlign uses two gradient alignment mechanisms derived from PAC-Bayesian analysis to reduce variance in local training and distortion in aggregation, yielding state-of-the-art personalization in federated learning.
-
Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid
A formalized Minimal Cognitive Grid ranks computational models of analogy and metaphor by alignment with cognitive theories using Functional/Structural Ratio, Generality, and Performance Match dimensions.
-
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
-
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.
-
Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety
Fine-tuned 8B LLMs produce children's English reading stories with better difficulty control and safety than zero-shot GPT-4o and Llama 3.3 70B.
-
Enhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword Bridging
Conversational scenario modeling from user profiles and domain knowledge, combined with intent-keyword bridging, improves proactivity, fluency, and informativeness in target-guided proactive dialogue systems.
-
A Reproducibility Analysis of PO4ISR: Diagnosing and Mitigating Semantic Drift in LLM-Based Session Recommendation
Reproducibility study diagnoses semantic drift in PO4ISR and introduces PO4ISR++ with reflexive prompting that restores performance with gains up to 54% on Games and 96% on Bundle.