DAIN reframes multimodal fusion as dynamic agent collaboration with sparse activation, claiming SOTA results including 2.6% accuracy gain on ADNI across five benchmarks.
FineVideo: Afine-graineddatasetforvideounderstanding.arXiv preprint arXiv:2405.00000
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Presents a diagnostic framework for semantic ID tokenizer failures using overlap and capacity metrics and proposes DRQ to separate geometry from distribution matching.
LiteFrame is an efficient vision encoder backbone trained with Compressed Token Distillation and Language Model Adaptation to scale frame count in Video LLMs while cutting latency and raising accuracy.
Neural networks for HEP tasks can be fooled at significant rates by subtle perturbations inside uncertainty envelopes, revealing hidden systematics not captured by conventional methods.
SGTO-MAS applies Gorilla Troops Optimization to formulate multi-agent LLM coordination as a constrained optimization problem, reporting average performance of 0.5281, consensus 0.8764, risk 0.3000, and 4.04 agents selected across 500 runs.
citing papers explorer
-
DAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal Reasoning
DAIN reframes multimodal fusion as dynamic agent collaboration with sparse activation, claiming SOTA results including 2.6% accuracy gain on ADNI across five benchmarks.
-
Decoupled Residual Quantization for Robust Semantic IDs in Recommendation
Presents a diagnostic framework for semantic ID tokenizer failures using overlap and capacity metrics and proposes DRQ to separate geometry from distribution matching.
-
LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs
LiteFrame is an efficient vision encoder backbone trained with Compressed Token Distillation and Language Model Adaptation to scale frame count in Video LLMs while cutting latency and raising accuracy.
-
Uncovering Hidden Systematics in Neural Network Models for High Energy Physics
Neural networks for HEP tasks can be fooled at significant rates by subtle perturbations inside uncertainty envelopes, revealing hidden systematics not captured by conventional methods.
-
SGTO-MAS: Secure Gorilla Troops Optimization for Multi-Agent LLM Systems
SGTO-MAS applies Gorilla Troops Optimization to formulate multi-agent LLM coordination as a constrained optimization problem, reporting average performance of 0.5281, consensus 0.8764, risk 0.3000, and 4.04 agents selected across 500 runs.