EyeMulator augments CodeLLM fine-tuning loss with token weights derived from human eye-tracking scan paths, producing large gains on code translation and summarization across StarCoder, Llama-3.2 and DeepSeek-Coder.
first come, first go
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
A conditional point-cloud flow matching model maps motor actuation to 3D geometry of tendon-driven continuum robots and outperforms prior self-modeling methods on simulated and real 2- and 3-module hardware.
SSL representation disentangles skill scheduling, structure, and logic using an LLM normalizer, improving skill discovery MRR@50 from 0.649 to 0.729 and risk assessment macro F1 from 0.409 to 0.509 over text baselines.
GraphRAG-IRL fuses graph-grounded MaxEnt IRL pre-ranking with persona-guided LLM re-ranking to deliver up to 16.8% NDCG@10 gains over IRL-only baselines on MovieLens and consistent 4-6% gains on KuaiRand.
Multi-modal BNN surrogates with conjugate last-layer SVI estimation improve prediction accuracy and uncertainty quantification over uni-modal baselines for scalar and time-series data with missing observations.
Embodied LLM agents exhibit emergent collaborative behaviors indicating mental models of partners in a color-matching game, detected via LLM judges and supported by positive user feedback.
An active inference model shows normative and explicit cues raise the chance of successful road conflict resolution but can cause collisions if agents violate expectations.
citing papers explorer
-
EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention
EyeMulator augments CodeLLM fine-tuning loss with token weights derived from human eye-tracking scan paths, producing large gains on code translation and summarization across StarCoder, Llama-3.2 and DeepSeek-Coder.
-
Continuum Robot Modeling with Action Conditioned Flow Matching
A conditional point-cloud flow matching model maps motor actuation to 3D geometry of tendon-driven continuum robots and outperforms prior self-modeling methods on simulated and real 2- and 3-module hardware.
-
From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
SSL representation disentangles skill scheduling, structure, and logic using an LLM normalizer, improving skill discovery MRR@50 from 0.649 to 0.729 and risk assessment macro F1 from 0.409 to 0.509 over text baselines.
-
GraphRAG-IRL: Personalized Recommendation with Graph-Grounded Inverse Reinforcement Learning and LLM Re-ranking
GraphRAG-IRL fuses graph-grounded MaxEnt IRL pre-ranking with persona-guided LLM re-ranking to deliver up to 16.8% NDCG@10 gains over IRL-only baselines on MovieLens and consistent 4-6% gains on KuaiRand.
-
Multi-modal Bayesian Neural Network Surrogates with Conjugate Last-Layer Estimation
Multi-modal BNN surrogates with conjugate last-layer SVI estimation improve prediction accuracy and uncertainty quantification over uni-modal baselines for scalar and time-series data with missing observations.
-
Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior
Embodied LLM agents exhibit emergent collaborative behaviors indicating mental models of partners in a color-matching game, detected via LLM judges and supported by positive user feedback.
-
Resolving space-sharing conflicts in road user interactions through uncertainty reduction: An active inference-based computational model
An active inference model shows normative and explicit cues raise the chance of successful road conflict resolution but can cause collisions if agents violate expectations.