Search Results for author:
Found 29 papers, 22 papers with code
VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
Recent studies have shown that long chain-of-thought (CoT) reasoning can significantly enhance the performance of large language models (LLMs) on complex tasks.
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
Remarkably, our experiments demonstrate that DTD achieves an 82. 8% reduction in video tokens while maintaining 98% performance on StreamingBench, revealing that over 80% of visual content in streaming videos is naturally redundant without requiring language guidance.
Kimi-VL Technical Report
We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2. 8B parameters in its language decoder (Kimi-VL-A3B).
SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
Motivated by the success of Reinforcement Learning with Verifiable Reward (RLVR) in unlocking LLM reasoning abilities, this work aims to improve MLLMs in video spatial reasoning through the RLVR paradigm.
TEMPLE:Temporal Preference Learning of Video LLMs via Difficulty Scheduling and Pre-SFT Alignment
We further analyze the transferability of DPO data across architectures and the role of difficulty scheduling in optimization.
UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
To evaluate the performance of automatic metrics in unified AIGV evaluation, we introduce a benchmark called UVE-Bench.
BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, yet generating reliable reasoning processes remains a significant challenge.
PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension
To provide a comprehensive evaluation, PunchBench incorporates diverse question formats and image-captions from various domains.
Temporal Reasoning Transfer from Text to Video
Video Large Language Models (Video LLMs) have shown promising capabilities in video comprehension, yet they struggle with tracking temporal changes and reasoning about temporal relationships.
DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
Specifically, we trace back the semantic relevance flow from generated language tokens to raw visual encoder patches and the intermediate outputs produced by projectors.
Towards Multimodal Video Paragraph Captioning Models Robust to Missing Modality
Video paragraph captioning (VPC) involves generating detailed narratives for long videos, utilizing supportive modalities such as speech and event boundaries.
TempCompass: Do Video LLMs Really Understand Videos?
Motivated by these two problems, we propose the \textbf{TempCompass} benchmark, which introduces a diversity of temporal aspects and task formats.
VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models
The ability to perceive how objects change over time is a crucial ingredient in human intelligence.
FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation
The multi-aspect categorization of FETV enables fine-grained analysis of the metrics' reliability in different scenarios.
COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models
Motivated by such considerations, we propose a collaborative optimization for PLMs that integrates static model compression and dynamic inference acceleration.
Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering
To this end, we systematically study the design of a training and compression pipeline to search the subnetworks, as well as the assignment of sparsity to different modality-specific modules.
A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models
In response to the efficiency problem, recent studies show that dense PLMs can be replaced with sparse subnetworks without hurting the performance.
Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning
However, these models reveal a trade-off that the improvements on OOD data severely sacrifice the performance on the in-distribution (ID) data (which is dominated by the biased samples).
Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA
To overcome this limitation, we propose a new dataset that considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.
Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training
Firstly, we discover that the success of magnitude pruning can be attributed to the preserved pre-training performance, which correlates with the downstream transferability.
Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation
In this paper, however, we observe that although distilling the teacher's hidden state knowledge (HSK) is helpful, the performance gain (marginal utility) diminishes quickly as more HSK is distilled.
ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques
Based on the empirical findings, our best compressed model, dubbed Refined BERT cOmpreSsion with InTegrAted techniques (ROSITA), is $7. 5 \times$ smaller than BERT while maintains $98. 5\%$ of the performance on five tasks of the GLUE benchmark, outperforming the previous BERT compression methods with similar parameter budget.
Learning Class-Transductive Intent Representations for Zero-shot Intent Detection
A critical problem behind these limitations is that the representations of unseen intents cannot be learned in the training stage.
Unsupervised Pre-training for Natural Language Generation: A Literature Review
They are classified into architecture-based methods and strategy-based methods, based on their way of handling the above obstacle.
Self-Adaptive Scaling for Learnable Residual Structure
Residual has been widely applied to build deep neural networks with enhanced feature propagation and improved accuracy.
Ranking and Sampling in Open-Domain Question Answering
Open-domain question answering (OpenQA) aims to answer questions based on a number of unlabeled paragraphs.
Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
In vision-and-language grounding problems, fine-grained representations of the image are considered to be of paramount importance.
simNet: Stepwise Image-Topic Merging Network for Generating Detailed and Comprehensive Image Captions
The encode-decoder framework has shown recent success in image captioning.
