WARP recovers training domain mixtures from fine-tuned model weights using weight-space interpolation via model merging to generate pseudo-checkpoints and geometric features mapped to proportions.
hub
arXiv preprint arXiv:2402.01761 , year=
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
representative citing papers
An argument paper reframes LLM explainability as an embodied, situated practice based on Dourish and enactivist cognition, identifying ontological obstacles in internal explanations and advocating affordance-based designs.
OceanCBM is the first concept bottleneck model for spatiotemporal ocean prediction that uses mixed supervision on physical concepts and a free concept to deliver consistent mechanistic representations for mixed layer heat content forecasts.
DECO is a sparse MoE architecture with ReLU-based routing, learnable expert scaling, and NormSiLU activation that matches dense Transformer performance at 20% expert activation and delivers 2.93x speedup on Jetson AGX Orin.
The Cylindrical Representation Hypothesis (CRH) models LLM representations as a central axis for concept activation surrounded by a normal plane containing sensitive sectors that determine steering sensitivity and introduce intrinsic uncertainty.
The paper introduces the Agentic Risk Standard (ARS) as a payment settlement framework that delivers predefined compensation for AI agent execution failures, misalignment, or unintended outcomes.
LLMs systematically let surface heuristics override unstated constraints; a new 500-item benchmark quantifies this and shows goal-decomposition prompting partially mitigates it.
GRAPHIC interprets confusion matrices from linear classifiers on intermediate layers as graphs to visualize and quantify class confusion dynamics in deep learning.
MoveFM-R is a framework that bridges mobility foundation models and LLMs using semantically enhanced location encoding, progressive curriculum alignment, and interactive self-reflection to generate plausible trajectories from language inputs.
LLM framework combines network topology and domain knowledge for iterative DSM sequencing optimization and outperforms stochastic and deterministic baselines on convergence speed and solution quality.
AnnotateThis lets users improve LLM annotations for climate change mitigation pessimism on social media, yielding 0.15 higher F-Measure and 0.23 higher accuracy than automated prompt refinement when ground truth labels are available.
The authors propose creating data probes—synthetic sequences from defined random processes—to reveal how data properties drive LLM behavior across workflow stages.
Large Sensor Models trained on large-scale multimodal wearable data can provide a scalable, general framework for wearable AI by learning transferable representations across modalities and tasks.
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.
Perceptual geometry for color, pitch, emotion and taste emerges transiently in intermediate layers of transformer LLMs despite purely textual training.
citing papers explorer
-
WARP: Weight-Space Analysis for Recovering Training Data Portfolios
WARP recovers training domain mixtures from fine-tuned model weights using weight-space interpolation via model merging to generate pseudo-checkpoints and geometric features mapped to proportions.
-
Embodied Explainability and Ontological Obstacles: Why We Struggle to Explain the Answers of Large Language Models (LLMs)
An argument paper reframes LLM explainability as an embodied, situated practice based on Dourish and enactivist cognition, identifying ontological obstacles in internal explanations and advocating affordance-based designs.
-
OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
OceanCBM is the first concept bottleneck model for spatiotemporal ocean prediction that uses mixed supervision on physical concepts and a free concept to deliver consistent mechanistic representations for mixed layer heat content forecasts.
-
DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices
DECO is a sparse MoE architecture with ReLU-based routing, learnable expert scaling, and NormSiLU activation that matches dense Transformer performance at 20% expert activation and delivers 2.93x speedup on Jetson AGX Orin.
-
The Cylindrical Representation Hypothesis for Language Model Steering
The Cylindrical Representation Hypothesis (CRH) models LLM representations as a central axis for concept activation surrounded by a normal plane containing sensitive sectors that determine steering sensitivity and introduce intrinsic uncertainty.
-
Quantifying Trust: Financial Risk Management for Trustworthy AI Agents
The paper introduces the Agentic Risk Standard (ARS) as a payment settlement framework that delivers predefined compensation for AI agent execution failures, misalignment, or unintended outcomes.
-
The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
LLMs systematically let surface heuristics override unstated constraints; a new 500-item benchmark quantifies this and shows goal-decomposition prompting partially mitigates it.
-
The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning
GRAPHIC interprets confusion matrices from linear classifiers on intermediate layers as graphs to visualize and quantify class confusion dynamics in deep learning.
-
MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning
MoveFM-R is a framework that bridges mobility foundation models and LLMs using semantically enhanced location encoding, progressive curriculum alignment, and interactive self-reflection to generate plausible trajectories from language inputs.
-
Large Language Models for Combinatorial Optimization of Design Structure Matrix
LLM framework combines network topology and domain knowledge for iterative DSM sequencing optimization and outperforms stochastic and deterministic baselines on convergence speed and solution quality.
-
AnnotateThis: Analyzing a human-LLM system for annotating social media data with the concept of climate change mitigation pessimism
AnnotateThis lets users improve LLM annotations for climate change mitigation pessimism on social media, yielding 0.15 higher F-Measure and 0.23 higher accuracy than automated prompt refinement when ground truth labels are available.
-
Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance
The authors propose creating data probes—synthetic sequences from defined random processes—to reveal how data properties drive LLM behavior across workflow stages.
-
Wearable AI in the Era of Large Sensor Models
Large Sensor Models trained on large-scale multimodal wearable data can provide a scalable, general framework for wearable AI by learning transferable representations across modalities and tasks.
-
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.
-
Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations
Perceptual geometry for color, pitch, emotion and taste emerges transiently in intermediate layers of transformer LLMs despite purely textual training.