Advanced Deep Learning

INSPIRED BY THE PROMPT LEARNING IN NATURAL LANGUAGE PROCESSING (NLP), WHICH HAS PRESENTED SIGNIFICANT EFFECTIVENESS IN LEVERAGING PRIOR KNOWLEDGE FOR VARIOUS NLP TASKS, WE STUDY THE PROMPTING TOPIC FOR GRAPHS WITH THE MOTIVATION OF FILLING THE GAP BETWEEN PRE-TRAINED MODELS AND VARIOUS GRAPH TASKS.

WE PRESENT THE ALL-SEEING (AS) PROJECT: A LARGE-SCALE DATA AND MODEL FOR RECOGNIZING AND UNDERSTANDING EVERYTHING IN THE OPEN WORLD.

WE PRESENT NNVISR - AN OPEN-SOURCE FILTER PLUGIN FOR THE VAPOURSYNTH VIDEO PROCESSING FRAMEWORK, WHICH FACILITATES THE APPLICATION OF NEURAL NETWORKS FOR VARIOUS KINDS OF VIDEO ENHANCING TASKS, INCLUDING DENOISING, SUPER RESOLUTION, INTERPOLATION, AND SPATIO-TEMPORAL SUPER-RESOLUTION.

IN THIS WORK, WE AIM TO BRIDGE THIS GAP BY CONDUCTING A RETROSPECTIVE ANALYSIS OF RECENT WORKS IN OFFLINE RL AND PROPOSE REBRAC, A MINIMALISTIC ALGORITHM THAT INTEGRATES SUCH DESIGN ELEMENTS BUILT ON TOP OF THE TD3+BC METHOD.

ACCURATE SAMPLING IS IMPORTANT TO PROVIDE A PRECISE COUPLING OF GEOMETRY AND RADIANCE; AND (III) IT ALLOWS EFFICIENT UNSUPERVISED DISENTANGLEMENT OF SHAPE AND APPEARANCE IN VOLUME RENDERING.

LARGE LANGUAGE MODELS (LLMS) HAVE SEEN AN IMPRESSIVE WAVE OF ADVANCES RECENTLY, WITH MODELS NOW EXCELLING IN A VARIETY OF TASKS, SUCH AS MATHEMATICAL REASONING AND PROGRAM SYNTHESIS.

WE INTRODUCE LLAMA, A COLLECTION OF FOUNDATION LANGUAGE MODELS RANGING FROM 7B TO 65B PARAMETERS.

THIS REPORT PRESENTS THE TECHNICAL DETAILS OF OUR SUBMISSION ON THE EGO4D AUDIO-VISUAL (AV) AUTOMATIC SPEECH RECOGNITION CHALLENGE 2023 FROM THE OXFORDVGG TEAM.

LARGE LANGUAGE MODEL (LLM) BASED GENERATIVE AI SYSTEMS HAVE SEEN SIGNIFICANT PROGRESS IN RECENT YEARS.

WE TACKLE THE TASK OF CONDITIONAL MUSIC GENERATION.

MULTI-QUERY ATTENTION (MQA), WHICH ONLY USES A SINGLE KEY-VALUE HEAD, DRASTICALLY SPEEDS UP DER INFERENCE.

MOST VISUAL RECOGNITION STUDIES RELY HEAVILY ON CROWD-LABELLED DATA IN DEEP NEURAL NETWORKS (DNNS) TRAINING, AND THEY USUALLY TRAIN A DNN FOR EACH SINGLE VISUAL RECOGNITION TASK, LEADING TO A LABORIOUS AND TIME-CONSUMING VISUAL RECOGNITION PARADIGM.

ADDING THESE DATA IN A LIGHTWEIGHT FINETUNING STEP CAN SIGNIFICANTLY REDUCE SYCOPHANTIC BEHAVIOR ON HELD-OUT PROMPTS.

CALIBRATION-BASED METHODS HAVE DOMINATED RAW IMAGE DENOISING UNDER EXTREMELY LOW-LIGHT ENVIRONMENTS.

MOST WORK ON REWARD LEARNING HAS USED SIMULATED ENVIRONMENTS, BUT COMPLEX INFORMATION ABOUT VALUES IS OFTEN EXPRESSED IN NATURAL LANGUAGE, AND WE BELIEVE REWARD LEARNING FOR LANGUAGE IS A KEY TO MAKING RL PRACTICAL AND SAFE FOR REAL-WORLD TASKS.

LARGE LANGUAGE MODELS (LLMS) HAVE DEMONSTRATED REMARKABLE PERFORMANCE ACROSS A WIDE ARRAY OF NLP TASKS.

DATABASE ADMINISTRATORS (DBAS) PLAY A CRUCIAL ROLE IN MANAGING, MAINTAINING AND OPTIMIZING A DATABASE SYSTEM TO ENSURE DATA AVAILABILITY, PERFORMANCE, AND RELIABILITY.

IN THIS WORK, WE DEVELOP A UNIVERSAL SOLUTION TO VPR -- A TECHNIQUE THAT WORKS ACROSS A BROAD RANGE OF STRUCTURED AND UNSTRUCTURED ENVIRONMENTS (URBAN, OUTDOORS, INDOORS, AERIAL, UNDERWATER, AND SUBTERRANEAN ENVIRONMENTS) WITHOUT ANY RE-TRAINING OR FINE-TUNING.

IN THIS WORK, WE DEVELOP AND RELEASE LLAMA 2, A COLLECTION OF PRETRAINED AND FINE-TUNED LARGE LANGUAGE MODELS (LLMS) RANGING IN SCALE FROM 7 BILLION TO 70 BILLION PARAMETERS.

SYNTHETIC IMAGE DATASETS OFFER UNMATCHED ADVANTAGES FOR DESIGNING AND EVALUATING DEEP NEURAL NETWORKS: THEY MAKE IT POSSIBLE TO (I) RENDER AS MANY DATA SAMPLES AS NEEDED, (II) PRECISELY CONTROL EACH SCENE AND YIELD GRANULAR GROUND TRUTH LABELS (AND CAPTIONS), (III) PRECISELY CONTROL DISTRIBUTION SHIFTS BETWEEN TRAINING AND TESTING TO ISOLATE VARIABLES OF INTEREST FOR SOUND EXPERIMENTATION.