Research

IN THIS WORK, WE PROPOSE RETENTIVE NETWORK (RETNET) AS A FOUNDATION ARCHITECTURE FOR LARGE LANGUAGE MODELS, SIMULTANEOUSLY ACHIEVING TRAINING PARALLELISM, LOW-COST INFERENCE, AND GOOD PERFORMANCE.

LARGE LANGUAGE MODELS (LLMS) ARE BECOMING INCREASINGLY SMART AND AUTONOMOUS, TARGETING REAL-WORLD PRAGMATIC MISSIONS BEYOND TRADITIONAL NLP TASKS.

IN THIS , WE DEVELOP A NEW METHOD TO AUTOMATICALLY CONVERT 2D LINE DRAWINGS FROM THREE ORTHOGRAPHIC VIEWS INTO 3D CAD MODELS.

LARGE LANGUAGE MODELS (LLMS) ARE GAINING INCREASING POPULARITY IN BOTH ACADEMIA AND INDUSTRY, OWING TO THEIR UNPRECEDENTED PERFORMANCE IN VARIOUS APPLICATIONS.

EVALUATING LARGE LANGUAGE MODEL (LLM) BASED CHAT ASSISTANTS IS CHALLENGING DUE TO THEIR BROAD CAPABILITIES AND THE INADEQUACY OF EXISTING BENCHMARKS IN MEASURING HUMAN PREFERENCES.

THIS DEALS WITH THE PROBLEM OF AUDIO SOURCE SEPARATION.

WE INTRODUCE VOYAGER, THE FIRST LLM-POWERED EMBODIED LIFELONG LEARNING AGENT IN MINECRAFT THAT CONTINUOUSLY EXPLORES THE WORLD, ACQUIRES DIVERSE SKILLS, AND MAKES NOVEL DISCOVERIES WITHOUT HUMAN INTERVENTION.

WE PRESENT MAGIC123, A TWO-STAGE COARSE-TO-FINE APPROACH FOR HIGH-QUALITY, TEXTURED 3D MESHES GENERATION FROM A SINGLE UNPOSED IMAGE IN THE WILD USING BOTH2D AND 3D PRIORS.

IN ADDITION, WE FIND VALL-E COULD PRESERVE THE SPEAKER'S EMOTION AND ACOUSTIC ENVIRONMENT OF THE ACOUSTIC PROMPT IN SYNTHESIS.

SINGLE IMAGE 3D RECONSTRUCTION IS AN IMPORTANT BUT CHALLENGING TASK THAT REQUIRES EXTENSIVE KNOWLEDGE OF OUR NATURAL WORLD.

RECENTLY, THE DETR FRAMEWORK HAS EMERGED AS THE DOMINANT APPROACH FOR HUMAN--OBJECT INTERACTION (HOI) RESEARCH.

RECENT ADVANCEMENTS IN NEURAL VOCODING ARE PREDOMINANTLY DRIVEN BY GENERATIVE ADVERSARIAL NETWORKS (GANS) OPERATING IN THE TIME-DOMAIN.

MOST METHODS IN THIS DIRECTION DEVELOP TASKSPECIFIC MODELS THAT ARE TRAINED WITH TYPE-SPECIFIC LABELS, SUCH AS MOMENT RETRIEVAL (TIME INTERVAL) AND HIGHLIGHT DETECTION (WORTHINESS CURVE), WHICH LIMITS THEIR ABILITIES TO GENERALIZE TO VARIOUS VTG TASKS AND LABELS.

WE INTRODUCE OPENFLAMINGO, A FAMILY OF AUTOREGRESSIVE VISION-LANGUAGE MODELS RANGING FROM 3B TO 9B PARAMETERS.

OUR ANALYSIS SUGGESTS THAT INSTRUCTOR IS ROBUST TO CHANGES IN INSTRUCTIONS, AND THAT INSTRUCTION FINETUNING MITIGATES THE CHALLENGE OF TRAINING A SINGLE MODEL ON DIVERSE DATASETS.

IN THIS WORK, WE PRESENT A CONCEPTUALLY SIMPLE AND EFFECTIVE METHOD TO TRAIN A STRONG BILINGUAL/MULTILINGUAL MULTIMODAL REPRESENTATION MODEL.

IN THIS WORK, WE MEASURE AND IMPROVE THE FACTUAL ACCURACY OF LARGE-SCALE LMS FOR OPEN-ENDED TEXT GENERATION.

WHISPER IS ONE OF THE RECENT STATE-OF-THE-ART MULTILINGUAL SPEECH RECOGNITION AND TRANSLATION MODELS, HOWEVER, IT IS NOT DESIGNED FOR REAL TIME TRANSCRIPTION.

FURTHERMORE, WE DEMONSTRATE THAT THE POISSON SURFACE RECONSTRUCTION PROBLEM IS WELL-POSED IN THE LIMIT CASE BY SHOWING A UNIVERSAL APPROXIMATION THEOREM FOR THE SOLUTION OPERATOR OF THE POISSON EQUATION WITH DISTRIBUTIONAL DATA UTILIZING THE FOURIER NEURAL OPERATOR, WHICH PROVIDES A THEORETICAL FOUNDATION FOR OUR NUMERICAL RESULTS.

IN THIS WORK, WE EXTEND SUCH AN EDITING FRAMEWORK TO DIFFUSION MODELS AND PROPOSE DRAGDIFFUSION.