Trending Research
Language-conditioned Detection Transformer
We use this detector to pseudo-label images with image-level labels.
SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability
alibaba-damo-academy/FunASR
•
•
It possesses the advantages of AED-based model's accuracy, NAR model's efficiency, and explicit customization capacity of superior performance.
White-Box Transformers via Sparse Rate Reduction
ma-lab-berkeley/crate
•
•
NeurIPS 2023
Particularly, we show that the standard transformer block can be derived from alternating optimization on complementary parts of this objective: the multi-head self-attention operator can be viewed as a gradient descent step to compress the token sets by minimizing their lossy coding rate, and the subsequent multi-layer perceptron can be viewed as attempting to sparsify the representation of the tokens.
SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
First, we train a degradation-aware prompt extractor, which can generate accurate soft and hard semantic prompts even under strong degradation.
AlignBench: Benchmarking Chinese Alignment of Large Language Models
Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants.
Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models
We present a method to create interpretable concept sliders that enable precise control over attributes in image generations from diffusion models.
SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation
Zero-shot 6D object pose estimation involves the detection of novel objects with their 6D poses in cluttered scenes, presenting significant challenges for model generalizability.
XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech
yl4579/StyleTTS2
•
•
We present XPhoneBERT, the first multilingual model pre-trained to learn phoneme representations for the downstream text-to-speech (TTS) task.
RETVec: Resilient and Efficient Text Vectorizer
google-research/retvec
•
•
NeurIPS 2023
The RETVec embedding model is pre-trained using pair-wise metric learning to be robust against typos and character-level adversarial attacks.
GLM-130B: An Open Bilingual Pre-trained Model
thudm/chatglm
•
•
We introduce GLM-130B, a bilingual (English and Chinese) pre-trained language model with 130 billion parameters.
Ranked #1 on
Language Modelling
on BIG-bench-lite
