Ser-Nam Lim

AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer

Think Then Embed: Generative Context Improves Multimodal Embedding

ROPA : Robust parallel diffusion sampling

Revisiting Random Generation Order: Ordinal-Biased Random Training for Efficient Visual Autoregressive Models

Proof-Augmented Retrieval and Reasoning: Supervising Language models for Knowledge Graph Completion with Link Predictors

AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation

Robust Fact-Checking under Contaminated Evidence Sources via Claim Decomposition and Dynamic Reweighting

Delta Activations: A Representation for Finetuned Large Language Models

OP-LoRA: The Blessing of Dimensionality with Overparameterized Low-Rank Adaptation

CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation

Reward-Guided Trajectory Distillation for Accelerated Diffusion-Based Video Generation

Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising

Motion Score Matching in Video Generation

Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation

Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning

ESCA: Contextualizing Embodied Agents via Scene-Graph Generation

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

LASER: A Neuro-Symbolic Framework for Learning Spatio-Temporal Scene Graphs with Weak Supervision

Improving Soft Unification with Knowledge Graph Embedding Methods

Towards Cross-modal Backward-compatible Representation Learning for Vision-Language Models

Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning

AnyView: Few Shot Personalized View Transfer

$\text{Slerp}^{+}$: Spherical Linear Interpolation for Unified Compositional Retrieval

Improving Soft Unification with Knowledge Graph Embedding Methods

Vector Quantization By Distribution Matching

LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence

LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models