CCTVBench exposes a large gap between standard QA accuracy and contrastive consistency in traffic video reasoning for multimodal LLMs and introduces C-TCD to narrow that gap.
hub Canonical reference
arXiv preprint arXiv:2312.14150 , year=
Canonical reference. 100% of citing Pith papers cite this work as background.
16
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
fields
cs.CV 16roles
background 5polarities
background 5representative citing papers
MME-RealWorld is the largest manually annotated high-resolution benchmark for MLLMs, where even the best models achieve less than 60% accuracy on challenging real-world tasks.
TRIP-Evaluate is a new open multimodal benchmark with 837 text, image, and point-cloud items organized by a role-task-knowledge taxonomy to evaluate large models on transportation workflows.
AlphaDrive uses GRPO-based RL rewards and two-stage SFT+RL training on VLMs to improve autonomous driving planning performance and efficiency while producing emergent multimodal capabilities.
ADvLM is the first visual adversarial attack framework for VLMs in autonomous driving, using semantic-invariant induction via LLM-generated prompt libraries and scenario-associated attention-based enhancement to achieve SOTA attack effectiveness across benchmarks and real-world tests.
ChainFlow-VLA unifies autoregressive causal trajectory modes with VLM-conditioned diffusion refinement to reach 94.85 on NAVSIM v1, matching human performance.
EgoDyn-Bench reveals a perception bottleneck in vision-centric foundation models: ego-motion logic derives from language while visual input adds negligible signal, with explicit trajectories restoring consistency.
OneDrive unifies heterogeneous decoding in a single VLM transformer decoder for end-to-end driving, achieving 0.28 L2 error and 0.18 collision rate on nuScenes plus 86.8 PDMS on NAVSIM.
BADAS-2.0 scales collision anticipation with a 178k-video long-tail benchmark built via active oracle selection, 7-12x faster distilled edge models, and object-centric attention heatmaps plus VLM-based textual reasoning.
OmniDrive-R1 boosts VLM reasoning score from 51.77% to 80.35% and answer accuracy from 37.81% to 73.62% on DriveLMM-o1 via reinforcement-driven interleaved multi-modal chain-of-thought with annotation-free grounding.
B4DL provides a new benchmark, scalable data generation pipeline, and MLLM architecture for direct spatio-temporal reasoning on raw 4D LiDAR data.
DriveMoE applies scene-specialized Vision MoE and skill-specialized Action MoE to a VLA baseline to achieve SOTA closed-loop performance on Bench2Drive.
Senna decouples language-based high-level planning from an LVLM with low-level trajectory prediction from an E2E model, reporting 27% lower planning error and 33% lower collisions after pre-training on DriveX and fine-tuning on nuScenes.
DriveVLM adds vision-language models with scene description, analysis, and hierarchical planning modules to autonomous driving, paired with a hybrid DriveVLM-Dual system tested on nuScenes and SUP-AD datasets and deployed on a production vehicle.
EponaV2 advances perception-free driving world models by forecasting comprehensive future 3D geometry and semantic representations, achieving SOTA planning performance on NAVSIM benchmarks.
Introduces structured NuScenes-S dataset and 0.9B FastDrive VLM claiming 20% higher decision accuracy and over 10x inference speedup versus larger unstructured VLMs.
citing papers explorer
-
CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs
CCTVBench exposes a large gap between standard QA accuracy and contrastive consistency in traffic video reasoning for multimodal LLMs and introduces C-TCD to narrow that gap.
-
MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
MME-RealWorld is the largest manually annotated high-resolution benchmark for MLLMs, where even the best models achieve less than 60% accuracy on challenging real-world tasks.
-
TRIP-Evaluate: An Open Multimodal Benchmark for Evaluating Large Models in Transportation
TRIP-Evaluate is a new open multimodal benchmark with 837 text, image, and point-cloud items organized by a role-task-knowledge taxonomy to evaluate large models on transportation workflows.
-
AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
AlphaDrive uses GRPO-based RL rewards and two-stage SFT+RL training on VLMs to improve autonomous driving planning performance and efficiency while producing emergent multimodal capabilities.
-
Visual Adversarial Attack on Vision-Language Models for Autonomous Driving
ADvLM is the first visual adversarial attack framework for VLMs in autonomous driving, using semantic-invariant induction via LLM-generated prompt libraries and scenario-associated attention-based enhancement to achieve SOTA attack effectiveness across benchmarks and real-world tests.
-
ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
ChainFlow-VLA unifies autoregressive causal trajectory modes with VLM-conditioned diffusion refinement to reach 94.85 on NAVSIM v1, matching human performance.
-
EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving
EgoDyn-Bench reveals a perception bottleneck in vision-centric foundation models: ego-motion logic derives from language while visual input adds negligible signal, with explicit trajectories restoring consistency.
-
OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models
OneDrive unifies heterogeneous decoding in a single VLM transformer decoder for end-to-end driving, achieving 0.28 L2 error and 0.18 collision rate on nuScenes plus 86.8 PDMS on NAVSIM.
-
Beyond the Beep: Scalable Collision Anticipation and Real-Time Explainability with BADAS-2.0
BADAS-2.0 scales collision anticipation with a 178k-video long-tail benchmark built via active oracle selection, 7-12x faster distilled edge models, and object-centric attention heatmaps plus VLM-based textual reasoning.
-
OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving
OmniDrive-R1 boosts VLM reasoning score from 51.77% to 80.35% and answer accuracy from 37.81% to 73.62% on DriveLMM-o1 via reinforcement-driven interleaved multi-modal chain-of-thought with annotation-free grounding.
-
B4DL: A Benchmark for 4D LiDAR LLM in Spatio-Temporal Understanding
B4DL provides a new benchmark, scalable data generation pipeline, and MLLM architecture for direct spatio-temporal reasoning on raw 4D LiDAR data.
-
DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving
DriveMoE applies scene-specialized Vision MoE and skill-specialized Action MoE to a VLA baseline to achieve SOTA closed-loop performance on Bench2Drive.
-
Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving
Senna decouples language-based high-level planning from an LVLM with low-level trajectory prediction from an E2E model, reporting 27% lower planning error and 33% lower collisions after pre-training on DriveX and fine-tuning on nuScenes.
-
DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
DriveVLM adds vision-language models with scene description, analysis, and hierarchical planning modules to autonomous driving, paired with a hybrid DriveVLM-Dual system tested on nuScenes and SUP-AD datasets and deployed on a production vehicle.
-
EponaV2: Driving World Model with Comprehensive Future Reasoning
EponaV2 advances perception-free driving world models by forecasting comprehensive future 3D geometry and semantic representations, achieving SOTA planning performance on NAVSIM benchmarks.
-
Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving
Introduces structured NuScenes-S dataset and 0.9B FastDrive VLM claiming 20% higher decision accuracy and over 10x inference speedup versus larger unstructured VLMs.