BOOKMARKS introduces searchable bookmarks as reusable answers to storyline questions, enabling active initialization and passive synchronization for more consistent role-playing agent memory than recurrent summarization.
Title resolution pending
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
Shapley values in product games equal the integral of a degree-(d-1) polynomial over [0,1], allowing provably exact or near-exact computation via Gauss-Legendre quadrature with O(d m_q) work.
Neurons exhibit concept-conditioned activation ranges forming Gaussian-like distributions with minimal overlap, and range-based interventions via NeuronLens outperform neuron-level masking in targeted manipulation with reduced collateral effects.
Introduces LOES, a constructive spectral method to select task-discriminative subspaces from intermediate layer embeddings, and GeoReg for enforcing simplicial class geometry during fine-tuning, with reported gains increasing with model depth across modalities.
CADI quantifies the preservation of relative cluster angles in low-dimensional projections using internal angles from point triples.
DRO-REBEL delivers scalable DRO-based online LLM alignment via relative reward regression, with O~(sqrt(d/n)) parameter error bounds and first parametric O~(d/n) rate under preference shift.
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
citing papers explorer
-
BOOKMARKS: Efficient Active Storyline Memory for Role-playing
BOOKMARKS introduces searchable bookmarks as reusable answers to storyline questions, enabling active initialization and passive synchronization for more consistent role-playing agent memory than recurrent summarization.
-
QuadraSHAP: Stable and Scalable Shapley Values for Product Games via Gauss-Legendre Quadrature
Shapley values in product games equal the integral of a degree-(d-1) polynomial over [0,1], allowing provably exact or near-exact computation via Gauss-Legendre quadrature with O(d m_q) work.
-
Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution
Neurons exhibit concept-conditioned activation ranges forming Gaussian-like distributions with minimal overlap, and range-based interventions via NeuronLens outperform neuron-level masking in targeted manipulation with reduced collateral effects.
-
Uncovering the Latent Potential of Deep Intermediate Representations
Introduces LOES, a constructive spectral method to select task-discriminative subspaces from intermediate layer embeddings, and GeoReg for enforcing simplicial class geometry during fine-tuning, with reported gains increasing with model depth across modalities.
-
Class Angular Distortion Index for Dimensionality Reduction
CADI quantifies the preservation of relative cluster angles in low-dimensional projections using internal angles from point triples.
-
Online Distributionally Robust LLM Alignment via Regression to Relative Reward
DRO-REBEL delivers scalable DRO-based online LLM alignment via relative reward regression, with O~(sqrt(d/n)) parameter error bounds and first parametric O~(d/n) rate under preference shift.
-
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
- To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios