deep-learning (235)
multimodal (83)
transformer (66)
llm (48)
diffusion (44)
clip (38)
text2image (25)
nerf (22)
bert (19)
3d (18)
attention (18)
blip (18)
gan (17)
flamingo (16)
image2image (16)
object-detection (16)
coca (14)
cvpr (14)
dataset (14)
review (14)
finance (13)
vit (13)
image-text-matching (12)
align (11)
audio (11)
blip2 (11)
cnn (11)
llama (11)
simvlm (11)
contrast-loss (10)
face (10)
llava (10)
personalize (10)
albef (9)
florence (9)
masked-language-modeling (9)
mlp (9)
swin-transformer (9)
differential-rendering (8)
dreambooth (8)
gpt (8)
image-caption (8)
resnet (8)
tool (8)
video (8)
bad (7)
glide (7)
read (7)
vq-vae (7)
2021 (6)
3dmm (6)
beit (6)
chatgpt (6)
dall-e2 (6)
distill (6)
flava (6)
git (6)
hubert (6)
ofa (6)
pali (6)
score-distillation-sampling (6)
self_supervised (6)
text2video (6)
2019 (5)
constrast-loss (5)
dream-booth (5)
instruct-blip (5)
mask-rcnn (5)
masked-image-modeling (5)
multimodality (5)
textual-inversion (5)
tracking (5)
vicuna (5)
vqa (5)
best-paper (4)
convolution (4)
detr (4)
differetial-render (4)
encoder-decoder (4)
imagen (4)
mobilenet (4)
prompt2prompt (4)
qformer (4)
quantization (4)
qwen-vl (4)
roberta (4)
sds (4)
signed-distance-function (4)
stable-diffusion (4)
synthetic (4)
video-chat (4)
vinvl (4)
alexnet (3)
asr (3)
auto-regressive (3)
clip-bert (3)
context (3)
dall-e (3)
domain-adaption (3)
fast-rcnn (3)
frozen (3)
ganfit (3)
giraffe (3)
graph (3)
history (3)
image-synthesize (3)
imagenet (3)
instant-booth (3)
jetson (3)
kosmos (3)
landmark-detection (3)
mesh (3)
meter (3)
misc (3)
mixup (3)
nvidia (3)
omnivl (3)
option (3)
palm (3)
pre-training (3)
reinforcement (3)
reinforcement-learning (3)
sam (3)
sdf (3)
segment (3)
segment-anything (3)
segmentation (3)
sft (3)
ssd (3)
style-gan (3)
stylegan (3)
text-image (3)
unclip (3)
unicl (3)
unified-io (3)
uniter (3)
univlp (3)
video-chatgpt (3)
vq-gan (3)
whisper (3)
zero-shot (3)
3d-object-detection (2)
aac (2)
ablef (2)
albedo (2)
alphapose (2)
aptx (2)
audio-gen (2)
audio-lm (2)
autoregressor (2)
avatar (2)
avatarme (2)
benchmark (2)
biggan (2)
blended-diffusion (2)
bluetooth (2)
body (2)
cat (2)
centernet (2)
chat-gpt (2)
clip-draw (2)
clip4clip (2)
cm3leon (2)
cog-vlm (2)
colmap (2)
composition (2)
conversation (2)
cornernet (2)
custom-diffusion (2)
cycle-gan (2)
dalle-2 (2)
dalle2 (2)
database (2)
deca (2)
deep-learining (2)
denoising (2)
densenet (2)
depth (2)
diff-sound (2)
diffvg (2)
dilated-convolution (2)
dino (2)
distillation (2)
dream-artist (2)
dreamfusion (2)
dreamix (2)
embedded (2)
embedding (2)
face-reconstruction (2)
fast-composer (2)
faster-rcnn (2)
fcn (2)
fcos (2)
few-shot-learning (2)
filip (2)
finetune (2)
flame (2)
focal-loss (2)
foundation-model (2)
global-attention (2)
gpt-4v (2)
gpt4 (2)
hardware (2)
hdr (2)
head-pose (2)
house (2)
hugging-gpt (2)
human (2)
identity (2)
image-classification (2)
in-the-wild (2)
instance-segmentation (2)
instruction-tuning (2)
instructpix2pix (2)
language-identification (2)
laser (2)
ldac (2)
lidar (2)
live (2)
longnet (2)
lora (2)
mac (2)
machine-translation (2)
mask-language-modeling (2)
mel-spectrogram (2)
mini-gpt (2)
mixture-of-experts (2)
mm-react (2)
mplug-owl2 (2)
multi-head-attention (2)
nas (2)
nas-fpn (2)
nasnet (2)
network-architecture-search (2)
neural-sound (2)
nllb (2)
note (2)
ode (2)
optical-flow (2)
optimal-transport (2)
oscar (2)
otter (2)
paint-by-words (2)
palette (2)
philosophy (2)
pi-gan (2)
pix2pix (2)
pixelnerf (2)
pose-estimation (2)
pretrain (2)
progressive-gan (2)
prompt (2)
query-transformer (2)
r-cnn (2)
response-ai (2)
retina-net (2)
rlhf (2)
robot (2)
sbc (2)
sdedit (2)
seamlessm4t (2)
seg-gpt (2)
self-attention (2)
self-supervise (2)
self-supervised (2)
semantic-segmentation (2)
siamfc (2)
siammask (2)
siamrpn (2)
single-image (2)
sktech-rnn (2)
sonar (2)
sound-stream (2)
speech-recognition (2)
squeezenet (2)
stargan (2)
style-clip-draw (2)
supervised-finetuning (2)
suti (2)
svg (2)
tag (2)
taming-encoder (2)
teacher-student (2)
text2live (2)
text2speech (2)
text2video-zero (2)
token (2)
triplane (2)
tts (2)
tune-a-video (2)
tutorial (2)
unet (2)
vad (2)
vae (2)
variational-auto-encoder (2)
vatt (2)
vector-ascent (2)
vector-fusion (2)
vector-graph (2)
vgg (2)
video-bert (2)
video-diffusion (2)
video-inpainting (2)
video-llama (2)
viper-gpt (2)
vision (2)
visual-bert (2)
vlbert (2)
voice-activity-detection (2)
w2v-bert (2)
wgan (2)
window-attention (2)
word-region-alignment (2)
word2vec (2)
xception (2)
yolo (2)
10pro (1)
204sn (1)
2dasl (1)
3d-face (1)
3d-gaussian (1)
3d-mesh (1)
3d-r2n2 (1)
3d-reconstruction (1)
3ddfa (1)
Belebele (1)
XRiSAWOZ (1)
accuracy (1)
acgan (1)
acm-mm-2019 (1)
action-unit-detection (1)
activation (1)
adafactor (1)
adam (1)
adb (1)
advancedeast (1)
adversial (1)
advserial (1)
align-prop (1)
alignment (1)
alpaca (1)
alphca (1)
altas (1)
amoebanet (1)
anchor-free (1)
animal (1)
animatable-nerf (1)
anti-face-spoofing (1)
anymal (1)
arcface (1)
arcore (1)
ardunio (1)
arkit (1)
arvr (1)
attack (1)
attenion (1)
attention-mix (1)
audio-synthesize (1)
auto-clip (1)
auto-mix (1)
autoencoder (1)
autonomous-driving (1)
autoregressive (1)
avface (1)
avlnet (1)
avnet (1)
axial-attention (1)
backdoor-attack (1)
bag-of-words (1)
bagging (1)
batch-normalization (1)
bay-area (1)
belmont (1)
beneficiary (1)
bigbigan (1)
binomial (1)
bit-compression (1)
black (1)
black-scholes (1)
blip-2 (1)
blip-diffusion (1)
body-pose (1)
boosting (1)
bownet (1)
brdf (1)
broker (1)
business (1)
byol (1)
c-corp (1)
c-rpn (1)
calibration (1)
cam3leon (1)
camera-estimation (1)
capex (1)
capital-expense (1)
caps-fusion (1)
capsnet (1)
caption (1)
cascade-rcnn (1)
casual (1)
casual-attention (1)
casual-masking (1)
catastrophic-forgetting (1)
cbir (1)
cfnet (1)
cgan (1)
chat (1)
chat-ir (1)
chichilla-law (1)
cir (1)
clap (1)
classification (1)
classifier-free-guidance (1)
claude (1)
cnn4g (1)
co-attention (1)
co-teaching (1)
co-vlm (1)
coarse (1)
cobit (1)
coco (1)
cocoop (1)
codi (1)
cogan (1)
cogview (1)
cola (1)
coloros (1)
compression (1)
comvt (1)
concept-distillation (1)
cones (1)
consistency (1)
constrastive (1)
constrastive-loss (1)
content-based-image-retrival (1)
continual-learning (1)
continuous-learning (1)
contrastive-adaptation-network (1)
contrastive-learning (1)
contrastive-loss (1)
control-net (1)
convnext (1)
convolution-neural-network (1)
convolutions (1)
coop (1)
craft (1)
cross-attenion (1)
cross-entropy (1)
cross-modality-fusion (1)
cups (1)
curriculum-learning (1)
cut-mix (1)
cycle-consistency (1)
cyclegan (1)
cyclic-shift (1)
d2nerf (1)
dann (1)
dasiamrpn (1)
data-augmentation (1)
data-balance (1)
data-cleaning (1)
dc-gan (1)
dcf (1)
dcgan (1)
dcnn (1)
dcrnn (1)
dda (1)
ddim (1)
decision-tree (1)
decoder (1)
deduplication (1)
deep-q (1)
deep-walk (1)
deepcut (1)
deeplab (1)
deepwalk (1)
deformation (1)
deit (1)
denosing (1)
densebox (1)
densesiam (1)
deoat (1)
depthwise-convolution (1)
detail (1)
detnas (1)
dfa-mcd (1)
dialog (1)
diff-quick-fix (1)
diffsound (1)
diffuse (1)
diffusion-det (1)
diht (1)
dilated-convolutions (1)
dion (1)
discrepancy (1)
discriminator (1)
dmtet (1)
dog (1)
dppm (1)
dranet (1)
dream-field (1)
dream-fusion (1)
dsiam (1)
dsm (1)
dsn (1)
dynamic (1)
e-ink (1)
e4t (1)
east (1)
ebsynth (1)
edge-tpu (1)
ediffi (1)
edit-a-video (1)
efficient (1)
efficientnet (1)
eg3d (1)
elastic (1)
electra (1)
elite (1)
encoder (1)
ernie (1)
esp32 (1)
esrgan (1)
euler (1)
ev (1)
exported (1)
expression (1)
expression-transfer (1)
extremenet (1)
eye (1)
eyeball (1)
face-animation (1)
face-attribute (1)
face-detection (1)
face-landmark (1)
face-landmark-detection (1)
face-tracking (1)
facebook (1)
faceformer (1)
facescape (1)
facewarehouse (1)
factorized-network (1)
faiss (1)
fastat (1)
fastboot (1)
fastboot-enhance (1)
fatezero (1)
fathom (1)
feedback (1)
feelvos (1)
fiber (1)
fid (1)
field-of-view (1)
film (1)
fixbi (1)
flan (1)
flash-attention (1)
flat-t5 (1)
flattened-network (1)
flownet (1)
fmcw (1)
focal-length (1)
ford (1)
fov (1)
foveabox (1)
fpn (1)
frequency-encoding (1)
frozen-in-time (1)
funit (1)
ga-rpn (1)
gairat (1)
ganpaint (1)
gat (1)
gat-lstm (1)
gaudi (1)
gaugan (1)
gcn (1)
gcnet (1)
generative-adversarial-network (1)
generator (1)
github (1)
glip (1)
glip-v2 (1)
glore (1)
google (1)
google-tango (1)
googlenet (1)
gpt-3 (1)
gpt3.5 (1)
gpt4v (1)
grad-align (1)
gradient-boosting (1)
graf (1)
graph-cnn (1)
graph-convolution-neural-network (1)
graphdatabase (1)
grit (1)
grounding-dino (1)
group (1)
group-lasso (1)
group-normalization (1)
grouped-convolution (1)
half-precision (1)
hallucination (1)
hard-negative-mining (1)
hash-encoding (1)
headnerf (1)
hero (1)
hierarchical (1)
hinge (1)
hololens (1)
hourglass (1)
hula-net (1)
human-nerf (1)
hyper-dreambooth (1)
hyper-v (1)
ibrnet (1)
ibuy (1)
icgan (1)
icml (1)
id-4 (1)
idea2img (1)
igan (1)
ijcai (1)
illumination (1)
image (1)
image-bind (1)
image-captioning (1)
image-recognition (1)
image-retrieval (1)
image-retrival (1)
image-search (1)
image-segmentation (1)
image-tag-alignment (1)
image2text (1)
imagen-video (1)
imglish (1)
improveddcgan (1)
imt (1)
in22 (1)
inception (1)
infogan (1)
infor-nce (1)
inkplate-10 (1)
instant-ngp (1)
instantflow (1)
instruct-gpt (1)
instruction-blip (1)
intel (1)
intern-video (1)
iris (1)
iron (1)
isomap (1)
jali (1)
jekyii (1)
kd3a (1)
key-frame (1)
keypoint-detection (1)
kinect (1)
kl-divergence (1)
klt (1)
kmeans (1)
knn (1)
laclip (1)
lamm (1)
lapgan (1)
laplacian-eigenmap (1)
latent (1)
layer-norm (1)
lease (1)
lemma (1)
lemon (1)
lenet (1)
libor (1)
lifting-style-gan (1)
light (1)
light-vit (1)
lighting (1)
linear-regression (1)
linux (1)
llama-adapter (1)
llc (1)
lle (1)
llm-agent (1)
llnet (1)
local (1)
log-log (1)
long-tail (1)
longmem (1)
loss (1)
low-light (1)
low-rank (1)
low-rank-approximation (1)
lsgan (1)
lucas-kanade (1)
lucid-data-dreaming (1)
lumigraph (1)
lvlm-ehub (1)
lxm-bert (1)
lxmert (1)
lyft (1)
m2det (1)
mach-e (1)
mae (1)
magneto (1)
make-a-video (1)
make-an-audio (1)
map (1)
marching-cube (1)
margin (1)
mart (1)
marvl (1)
mask-auto-encoder (1)
mask-dino (1)
mask-region-modeling (1)
masked-auto-encoder (1)
masked-lanuage-modeling (1)
masked-region-classification (1)
masked-video-prediction (1)
masked-visual-token-modeling (1)
masking (1)
mass (1)
matching (1)
math (1)
matrix (1)
matt-net (1)
matte (1)
mbllen (1)
mbst (1)
mcpl (1)
mdetr (1)
mds (1)
mean-teacher (1)
meda (1)
memo (1)
merged-attention (1)
merlot (1)
mesh-rcnn (1)
meshtalk (1)
metaverse (1)
mga-net (1)
mimic-it (1)
mini-gpt4 (1)
minist (1)
mix-of-show (1)
mixmatch (1)
mixnet (1)
mixture-volumetric-presentation (1)
mmbench (1)
mme (1)
mobile (1)
modality-switching-instruction-tunning (1)
model-merging (1)
monosdf (1)
morphnet (1)
motion (1)
mountain-view (1)
movidius (1)
movie-chat (1)
mplug-owl (1)
msr (1)
mubert (1)
mugen (1)
mulan (1)
multi-grain-attention (1)
multi-label (1)
multi-lingual (1)
multi-objective-learning (1)
multi-person (1)
multi-resolution (1)
multi-scale (1)
multi-scale-retinex (1)
multi-task (1)
multi-task-learning (1)
multi-view-stereo (1)
multiplane-image (1)
muse (1)
music-lm (1)
mvs-nerf (1)
mvsnet (1)
nano (1)
nce (1)
ne2210 (1)
ne2211 (1)
ne2213 (1)
ne2215 (1)
nearest-neighbor (1)
neo4j (1)
nerf-studio (1)
nerfies (1)
nerfusion (1)
network (1)
network-pruning (1)
neuman (1)
neuphysics (1)
neural (1)
neural-actor (1)
neural-architecture-search (1)
neural-atlas-layers (1)
neural-body (1)
nfnet (1)
nla (1)
no-3d (1)
noise-contrast-estimation (1)
noisy (1)
noisy-label (1)
normal (1)
normalization (1)
normlization (1)
nssm (1)
null-text-inversion (1)
nvdiffrec (1)
object-tracking (1)
obow (1)
obsidian (1)
octave (1)
octopus (1)
oculus (1)
office (1)
omnimatte (1)
oneplus (1)
open (1)
open-flamingo (1)
open-seed (1)
open-vocabulary (1)
opendoor (1)
openpose (1)
operating-expense (1)
opex (1)
opt (1)
optimizer (1)
orientdb (1)
osvos (1)
oxygenos (1)
paint-with-words (1)
pali3 (1)
palix (1)
panda-gpt (1)
pandas (1)
panet (1)
parti (1)
partnership (1)
pasta (1)
pcida (1)
perceiver (1)
perfusion (1)
persam (1)
pet (1)
pggan (1)
photo (1)
photorealistic (1)
pix2pix-hd (1)
pix2video (1)
pixel2mesh (1)
pixelink (1)
plan (1)
pmtd (1)
pnasnet (1)
poa (1)
point-tracking (1)
pointwise-convolution (1)
poly-former (1)
pose (1)
position-encoding (1)
position-encodings (1)
post-activation (1)
post-estimation (1)
post-script (1)
power-of-attorney (1)
pre-activation (1)
pre-train (1)
precision (1)
prefix-lm (1)
premvos (1)
pricing (1)
print (1)
privacy (1)
prnet (1)
proda (1)
profusion (1)
progressive-distillation (1)
prolific-dreamer (1)
prompt-contrast-loss (1)
proof (1)
prune (1)
psaf (1)
psenet (1)
psp (1)
pspnet (1)
pupil (1)
pynq (1)
pyramid (1)
pytorch (1)
q-former (1)
quanterion (1)
query-former (1)
r-fcn (1)
raft (1)
ram (1)
ran (1)
random-forest (1)
rank (1)
ranking (1)
rasnet (1)
raspberry-pi (1)
ray-march (1)
ray-trace (1)
rcan (1)
rdfn (1)
re-imagen (1)
real-estate (1)
recommendation (1)
reconstruction (1)
rectified-flow (1)
recurrent-neural-network (1)
redfin (1)
refinenet (1)
reflextion (1)
reformer (1)
register (1)
regnet (1)
reinforcement-learning-human-feedback (1)
relationship (1)
relative-position-encoding (1)
relightable (1)
residual-vector-quantization (1)
resnet-50 (1)
resnext (1)
resolution (1)
restoration (1)
retinex-net (1)
retrieval (1)
reward (1)
ricoh (1)
riffusion (1)
ringnet (1)
riren (1)
rmpe (1)
robust (1)
rodrigue (1)
rope (1)
rotation (1)
rotation-position-encoding (1)
rvq (1)
s-corp (1)
s2-attn (1)
sa-siam (1)
sagan (1)
sam-track (1)
san-carlos (1)
sat (1)
sbl (1)
scholes (1)
scribble (1)
securities-based-lending (1)
seed (1)
seem (1)
segment-anything-model (1)
segnet (1)
self-mod (1)
self-refine (1)
self-reflective (1)
selfies (1)
semantic-sam (1)
semi-supervised-learning (1)
semigan (1)
separable-convolution (1)
seperable-filter (1)
seq2seq (1)
sequence (1)
service (1)
sfm (1)
shift-short-attention (1)
shifted-window (1)
shikra (1)
shortcut (1)
shot (1)
siam-bm (1)
siamese (1)
siamese-network (1)
siamfc-tri (1)
siamrpn++ (1)
siggraph (1)
siglip (1)
sim-vlm (1)
simclr (1)
simpleclr (1)
simsiam (1)
single (1)
single-head-attention (1)
single-object-tracking (1)
sint (1)
sint++ (1)
sinusoid-encoding (1)
skip (1)
sknet (1)
slam (1)
sliding-window (1)
smpl (1)
sole-proprietorship (1)
sort (1)
soundstream (1)
spanbert (1)
sparse (1)
sparse-rcnn (1)
sparsity (1)
spectral-convolution (1)
specular (1)
speech-gpt (1)
spl (1)
srda (1)
srgan (1)
st-nerf (1)
stability (1)
stable (1)
stackgan (1)
story-dalle (1)
story-telling (1)
storydall-e (1)
streaming-llm (1)
strike (1)
struction-from-motion (1)
structsiam (1)
style-drop (1)
style-transfer (1)
subtitle (1)
super-resolution (1)
sv-dff (1)
swin (1)
synology (1)
syntax (1)
t5 (1)
ta3n (1)
taco (1)
tag2text (1)
tax (1)
teal (1)
teat (1)
tent (1)
tesla (1)
tet-gan (1)
tetrahedral (1)
text-detection (1)
text-image-synthesize (1)
textfield (1)
textmountain (1)
texture (1)
thundernet (1)
tic-clip (1)
time-of-flight (1)
timeline (1)
tips (1)
tof (1)
tokenflow (1)
tool-former (1)
tpt (1)
tpu (1)
tracker (1)
tracking-anything (1)
training (1)
transfer-learning (1)
transposed-convolution (1)
travel-salesman-problem (1)
traveling-salesman-problem (1)
triplet (1)
true-type (1)
tubevit (1)
u-net (1)
uber (1)
uda (1)
ultra96 (1)
umm-diffusion (1)
unilm (1)
unitbox (1)
univl (1)
unncany (1)
unsupervised-learning (1)
usb (1)
valor (1)
value (1)
variational-score-distillation (1)
vast (1)
veclip (1)
vector (1)
vector-quantization (1)
verification (1)
vfa (1)
vibert (1)
vid2actor (1)
vid2vid-zero (1)
vide-chatgpt (1)
video-caption (1)
video-editing (1)
video-object-segmentation (1)
video-p2p (1)
vidoe-clip (1)
vil-bert (1)
vilbert (1)
villa (1)
vilt (1)
violet (1)
virtualbox (1)
vision-illusion (1)
vision-transformer (1)
visprog (1)
visual-chat-gpt (1)
visual-chatgpt (1)
visual-grounding (1)
visual-localization (1)
visualbert (1)
vlog (1)
volkswagon (1)
voxel (1)
vpa (1)
vsd (1)
wavegrad (1)
weakly-self-supervised (1)
weather (1)
weight-decay (1)
wenlan (1)
wgan-gp (1)
whipser (1)
width (1)
window (1)
windows (1)
word-patch-alignment (1)
world (1)
wrinkle (1)
x-gpt (1)
xception-network (1)
xclip (1)
xenology (1)
xilinx (1)
xlnet (1)
xm-3600 (1)
xmem (1)
xpos (1)
yolox (1)
z (1)
zero-shot-learning (1)
zigzagnet (1)
zillow (1)
ziya (1)
zotero (1)
zynq (1)
周华健 (1)
天龙八部 (1)
林夕 (1)
歌词 (1)
武侠 (1)
难念的经 (1)
Qiang Zhang
Experienced Computer Vision and Machine Learning Engineer