Variable codebook sizes that increase along the sequence in visual tokenizers reduce generation FID scores significantly for autoregressive models on ImageNet.
Mixed citations
In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Mixed citation behavior. Most common role is background (50%).
9
Pith papers citing it
37
external citations · external index
Background
50% of classified citations
citation-role summary
background 3
baseline 1
dataset 1
method 1
citation-polarity summary
years
2026 9representative citing papers
Driver-WM is a driver-centric latent world model for causal rollout of in-cabin dynamics conditioned on out-cabin traffic, unifying kinematics forecasting with behavioral and emotional recognition via dual-stream architecture and gated injection.
Text-guided class-agnostic counting models exhibit significant weaknesses in grounding textual prompts to visual objects, as demonstrated by new negative-label and distractor tests on a multi-category dataset.
The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
Composer enables semantic-agnostic composition transfer from references and theme-driven planning via LVLMs to improve aesthetic quality in diffusion-based image generation.
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
MooD introduces continuous valence-arousal modeling with VA-aware retrieval and perception-enhanced guidance for efficient, controllable affective image editing, plus a new AffectSet dataset.
SportsTime plus Chain-of-Time Reasoning (temporal-reward GRPO and anchor-observe-infer) modestly lifts open-ended sports VideoQA and step-wise temporal grounding over 4B–8B MLLM baselines.
U-Define improves user control in LLM planning by letting people define hard rules and soft preferences in natural language with matching verification methods, raising usefulness and satisfaction scores.
citing papers explorer
-
Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation
Variable codebook sizes that increase along the sequence in visual tokenizers reduce generation FID scores significantly for autoregressive models on ImageNet.
-
Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
Driver-WM is a driver-centric latent world model for causal rollout of in-cabin dynamics conditioned on out-cabin traffic, unifying kinematics forecasting with behavioral and emotional recognition via dual-stream architecture and gated injection.
-
Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting
Text-guided class-agnostic counting models exhibit significant weaknesses in grounding textual prompts to visual objects, as demonstrated by new negative-label and distractor tests on a multi-category dataset.
-
Rethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language Model
The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
-
Advancing Aesthetic Image Generation via Composition Transfer
Composer enables semantic-agnostic composition transfer from references and theme-driven planning via LVLMs to improve aesthetic quality in diffusion-based image generation.
-
Stylistic Attribute Control in Latent Diffusion Models
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
-
MooD: Perception-Enhanced Efficient Affective Image Editing via Continuous Valence-Arousal Modeling
MooD introduces continuous valence-arousal modeling with VA-aware retrieval and perception-enhanced guidance for efficient, controllable affective image editing, plus a new AffectSet dataset.
-
Towards Temporal Compositional Reasoning in Long-Form Sports Videos
SportsTime plus Chain-of-Time Reasoning (temporal-reward GRPO and anchor-observe-infer) modestly lifts open-ended sports VideoQA and step-wise temporal grounding over 4B–8B MLLM baselines.
-
U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning
U-Define improves user control in LLM planning by letting people define hard rules and soft preferences in natural language with matching verification methods, raising usefulness and satisfaction scores.