IntentVLM uses forward-inverse modeling in a two-stage video-language setup to reach up to 80% accuracy on open-vocabulary intention recognition benchmarks, beating baselines by 30% and matching human performance.
Parameter-efficient fine-tuning for foundation models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
CURE disentangles LLM recommendation circuits into forget-specific, retain-specific, and task-shared modules with tailored update rules to achieve more effective unlearning than weighted baselines.
HiCoLoRA uses hierarchical LoRA with spectral domain-slot clustering, adaptive fusion, and semantic SVD initialization to achieve SOTA zero-shot DST on MultiWOZ and SGD.
citing papers explorer
-
IntentVLM: Open-Vocabulary Intention Recognition through Forward-Inverse Modeling with Video-Language Models
IntentVLM uses forward-inverse modeling in a two-stage video-language setup to reach up to 80% accuracy on open-vocabulary intention recognition benchmarks, beating baselines by 30% and matching human performance.
-
CURE:Circuit-Aware Unlearning for LLM-based Recommendation
CURE disentangles LLM recommendation circuits into forget-specific, retain-specific, and task-shared modules with tailored update rules to achieve more effective unlearning than weighted baselines.
-
HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST
HiCoLoRA uses hierarchical LoRA with spectral domain-slot clustering, adaptive fusion, and semantic SVD initialization to achieve SOTA zero-shot DST on MultiWOZ and SGD.