McAuley Lab UCSD
@McAuleyLabUCSD
Followers
296
Following
56
Media
0
Statuses
16
We're the McAuley lab @ucsd_cse with PI Prof. Julian McAuley! We work and tweet about cool #MachineLearning and #NLProc applications š§ š¤
San Diego, CA
Joined November 2021
RT @yupenghou97: š Releasing Amazon Reviews 2023 dataset! . With *500+M* user reviews, *48+M* items, *60+B* tokens, all from 33 categories,ā¦.
0
45
0
RT @noveens97: Q: Can we pre-train LLMs efficiently (and better?) via data pruning?.A: Yes!. Q: How?.A: (secret) Prompt LLMs for data qualiā¦.
0
40
0
RT @JeffDean: Gemini 1.5 Pro - A highly capable multimodal model with a 10M token context length. Today we are releasing the first demonstrā¦.
0
1K
0
RT @zacknovack: Fine-grained control/editing in text-to-music diffusion models w/NO TRAINING?. Presenting DITTO: Diffusion Inference-Time Tā¦.
0
49
0
RT @yupenghou97: Our paper on interesting findings about āLLMs & RecSysā has just been accepted as a full paper in #ecir2024. The most deliā¦.
github.com
[ECIR'24] Implementation of "Large Language Models are Zero-Shot Rankers for Recommender Systems" - RUCAIBox/LLMRank
0
8
0
RT @zacknovack: Lead sheets concisely describe music, but can we improve their compressive ability w.r.t. the original score?. Check out ouā¦.
0
5
0
RT @_akhaliq: Farzi Data: Autoregressive Data Distillation. paper page: study data distillation for auto-regressivā¦.
0
18
0
RT @ZhankuiHe: š¤ļø Are LLMs good Conversational Recommender Systems (CRS) ? .We (@McAuleyLabUCSD and @NetflixResearch) let LLMs generate movā¦.
0
5
0
RT @noveens97: Highly grateful! Definitely recommend the streamlined publication experience @TmlrOrg . For people intersted in data distillā¦.
0
3
0
RT @noveens97: Ecstatic to join @DeepMind as a research intern for the summer -- looking forward to new friends and being surrounded by theā¦.
0
2
0
0
2
0
RT @UCSDJacobs: Researchers @UCSanDiego developed algorithms to rid speech generated by online bots of offensive language, on social mediaā¦.
0
2
0
RT @mbodhisattwa: Announcing with shaky hands and much delight:.Our "conversational critiquing" paper is selected for "Highlights of ACM Reā¦.
0
1
0
RT @noveens97: Conventional #recsys wisdom: "better to go wide than deep". Our paper: go infinitely-wide, compute the solution in closed-foā¦.
0
97
0
RT @salu133445: Happy to share that our paper "Deep Performer: Score-to-Audio Music Performance Synthesis" has been accepted to @ieeeICASSPā¦.
0
10
0