Search Results for author:
Found 23 papers, 9 papers with code
MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning
Visual instruction tuning (VIT) has emerged as a crucial technique for enabling multi-modal large language models (MLLMs) to follow user instructions adeptly.
The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
Multimodal Reward Models (MM-RMs) are crucial for aligning Large Language Models (LLMs) with human preferences, particularly as LLMs increasingly interact with multimodal data.
Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch
Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences.
Scalable Oversight for Superhuman AI via Recursive Self-Critiquing
As AI capabilities increasingly surpass human proficiency in complex tasks, current alignment techniques including SFT and RLHF face fundamental challenges in ensuring reliable oversight.
SedarEval: Automated Evaluation using Self-Adaptive Rubrics
Using the same training data, our evaluator LM achieves a higher concordance rate with human grading results than other paradigms, including GPT-4, highlighting the superiority and efficiency of our approach.
NExtLong: Toward Effective Long-Context Training without Long Documents
Large language models (LLMs) with extended context windows have made significant strides yet remain a challenge due to the scarcity of long documents.
RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?
In this work, we explore the untapped potential of scaling Long Chain-of-Thought (Long-CoT) data to 1000k samples, pioneering the development of a slow-thinking model, RedStar.
Diff-Instruct*: Towards Human-Preferred One-step Text-to-image Generative Models
In this paper, we introduce the Diff-Instruct* (DI*), an image data-free approach for building one-step text-to-image generative models that align with human preference while maintaining the ability to generate highly realistic images.
Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?
Reward Models (RMs) are crucial for aligning language models with human preferences.
CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning
Large language models (LLMs) have made significant progress in natural language understanding and generation, driven by scalable pretraining and advanced finetuning.
Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models
Large language models (LLM) have prioritized expanding the context window from which models can incorporate more information.
Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic
Self-critic has become a crucial mechanism for enhancing the reasoning performance of LLMs.
MPI-Flow: Learning Realistic Optical Flow with Multiplane Images
The accuracy of learning-based optical flow estimation models heavily relies on the realism of the training datasets.
Recurrent Self-Supervised Video Denoising with Denser Receptive Field
However, under their blind spot constraints, previous self-supervised video denoising methods suffer from significant information loss and texture destruction in either the whole reference frame or neighbor frames, due to their inadequate consideration of the receptive field.
AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection
For video content creation and understanding, the shot boundary detection (SBD) is one of the most essential components in various scenarios.
Ranked #1 on
Camera shot boundary detection
on ClipShots
One-shot Implicit Animatable Avatars with Model-based Priors
Most of these methods fail to achieve realistic reconstruction when only a single image is available.
End-to-End Video Text Spotting with Transformer
Recent video text spotting methods usually require the three-staged pipeline, i. e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results.
A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer
Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data.
TransAug: Translate as Augmentation for Sentence Embeddings
In this paper, we present TransAug (Translate as Augmentation), which provide the first exploration of utilizing translated sentence pairs as data augmentation for text, and introduce a two-stage paradigm to advances the state-of-the-art sentence embeddings.
EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modeling
Extra rich non-paired single-modal text data is used for boosting the generalization of text branch.
Partial FC: Training 10 Million Identities on a Single Machine
The experiment demonstrates no loss of accuracy when training with only 10\% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on mainstream benchmarks.
Ranked #2 on
Face Identification
on MegaFace
EasyQuant: Post-training Quantization via Scale Optimization
The 8 bits quantization has been widely applied to accelerate network inference in various deep learning applications.
Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery
Hyperspectral image (HSI) recovery from a single RGB image has attracted much attention, whose performance has recently been shown to be sensitive to the camera spectral sensitivity (CSS).
