Introduces Bayesian Sensitivity Value (BSV) for causal inference sensitivity analysis based on evidence-derived priors and Monte Carlo estimation, applied to diabetes treatment effects.
Title resolution pending
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
representative citing papers
A GenAI-based method extracts representations from unstructured data and uses a neural network to fit marginal structural models that recover causal effects of treatment feature sequences including their positions.
InvEvolve evolves white-box inventory policies from LLMs with statistical safety guarantees and outperforms classical and deep learning methods on synthetic and real retail data.
Local linearity of LLM layers enables LQR-based closed-loop activation steering with theoretical tracking guarantees.
DeepSeek-V2 delivers top-tier open-source LLM performance using only 21B active parameters by compressing the KV cache 93.3% and cutting training costs 42.5% via MLA and DeepSeekMoE.
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
Summing outputs from separately trained QLoRA PEFT modules provides strong performance for attribute-controlled text generation, often matching or exceeding single-task modules even on single-attribute tests.
A hypernetwork generates meta-gating parameters for SwiGLU blocks to let LLMs adapt their nonlinearity to arbitrary textual conditions, outperforming finetuning and meta-learning baselines with reasonable generalization to unseen cases.
The LENS framework applied to 192 real-world settings shows moderate natural prompt distribution shifts cause 73% average performance loss in deployed LLMs, especially across user groups and regions.
Math reasoning gains in LLMs rarely transfer to general domains; RL tuning generalizes while SFT causes forgetting and representation drift.
VPiT enables pretrained LLMs to perform both visual understanding and generation by predicting discrete text tokens and continuous visual tokens, with understanding data proving more effective than generation-specific data.
CogVideoX generates coherent 10-second text-to-video outputs at high resolution using a 3D VAE, expert adaptive LayerNorm transformer, progressive training, and a custom data pipeline, claiming state-of-the-art results.
BADIT decomposes LLM parameters into orthogonal high-singular-value LoRA experts for basic abilities and applies spherical clustering of rank-1 components to reduce cross-task interference, outperforming prior methods on the SuperNI benchmark.
GIFT guides adapter fine-tuning on base models with confidence signals from instruction-tuned models before merging, yielding task-specialized models that outperform direct fine-tuning on math and knowledge benchmarks.
STK-Adapter adds Spatial-Temporal MoE, Event-Aware MoE, and Cross-Modality Alignment MoE to integrate evolving TKG graphs and event chains into LLMs, reducing information loss and improving extrapolation performance over prior methods.
mPLUG-Owl3 introduces hyper attention blocks to integrate vision and language for long image-sequence understanding and reports SOTA results on single-image, multi-image, and video benchmarks.
A context-aware synthetic augmentation framework with a hybrid clinical-language model improves psychological defense mechanism classification to 58.26% accuracy and 24.62% macro-F1 in low-resource conditions, outperforming the DMRS Co-Pilot baseline.
A neuro-symbolic system is proposed that uses formal logic to constrain LLM outputs so legal inferences stay faithful to source text.
Gemma 2 models achieve leading performance at their sizes by combining established Transformer modifications with knowledge distillation for the 2B and 9B variants.
citing papers explorer
-
Bayesian Sensitivity of Causal Inference Estimators under Evidence-Based Priors
Introduces Bayesian Sensitivity Value (BSV) for causal inference sensitivity analysis based on evidence-derived priors and Monte Carlo estimation, applied to diabetes treatment effects.
-
GenAI Powered Dynamic Causal Inference with Unstructured Data
A GenAI-based method extracts representations from unstructured data and uses a neural network to fit marginal structural models that recover causal effects of treatment feature sequences including their positions.
-
InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees
InvEvolve evolves white-box inventory policies from LLMs with statistical safety guarantees and outperforms classical and deep learning methods on synthetic and real retail data.
-
Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
Local linearity of LLM layers enables LQR-based closed-loop activation steering with theoretical tracking guarantees.
-
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
DeepSeek-V2 delivers top-tier open-source LLM performance using only 21B active parameters by compressing the KV cache 93.3% and cutting training costs 42.5% via MLA and DeepSeekMoE.
-
Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
-
Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation
Summing outputs from separately trained QLoRA PEFT modules provides strong performance for attribute-controlled text generation, often matching or exceeding single-task modules even on single-attribute tests.
-
Learn-to-learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM
A hypernetwork generates meta-gating parameters for SwiGLU blocks to let LLMs adapt their nonlinearity to arbitrary textual conditions, outperforming finetuning and meta-learning baselines with reasonable generalization to unseen cases.
-
Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance
The LENS framework applied to 192 real-world settings shows moderate natural prompt distribution shifts cause 73% average performance loss in deployed LLMs, especially across user groups and regions.
-
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Math reasoning gains in LLMs rarely transfer to general domains; RL tuning generalizes while SFT causes forgetting and representation drift.
-
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
VPiT enables pretrained LLMs to perform both visual understanding and generation by predicting discrete text tokens and continuous visual tokens, with understanding data proving more effective than generation-specific data.
-
CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
CogVideoX generates coherent 10-second text-to-video outputs at high resolution using a 3D VAE, expert adaptive LayerNorm transformer, progressive training, and a custom data pipeline, claiming state-of-the-art results.
-
Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
BADIT decomposes LLM parameters into orthogonal high-singular-value LoRA experts for basic abilities and applies spherical clustering of rank-1 components to reduce cross-task interference, outperforming prior methods on the SuperNI benchmark.
-
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
GIFT guides adapter fine-tuning on base models with confidence signals from instruction-tuned models before merging, yielding task-specialized models that outperform direct fine-tuning on math and knowledge benchmarks.
-
STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph Extrapolation
STK-Adapter adds Spatial-Temporal MoE, Event-Aware MoE, and Cross-Modality Alignment MoE to integrate evolving TKG graphs and event chains into LLMs, reducing information loss and improving extrapolation performance over prior methods.
-
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
mPLUG-Owl3 introduces hyper attention blocks to integrate vision and language for long image-sequence understanding and reports SOTA results on single-image, multi-image, and video benchmarks.
-
Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation
A context-aware synthetic augmentation framework with a hybrid clinical-language model improves psychological defense mechanism classification to 58.26% accuracy and 24.62% macro-F1 in low-resource conditions, outperforming the DMRS Co-Pilot baseline.
-
Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning
A neuro-symbolic system is proposed that uses formal logic to constrain LLM outputs so legal inferences stay faithful to source text.
-
Gemma 2: Improving Open Language Models at a Practical Size
Gemma 2 models achieve leading performance at their sizes by combining established Transformer modifications with knowledge distillation for the 2B and 9B variants.