📢 Today
@BU_Research
as a part of the weekly research seminars, 👨🎓 Xibin Bayes Zhou presents an advances in Language Models application for Protein. 🧬 Apparently, application of Language models to protein similar to NLP
🧵1/n
So far experimented 🧪 with LLaVa 1.5 and Idefics 9B at scale and they are quite handy out-of-the-box 📦
Eventhough, it is nice to see even smaller versions are out, that based on most recent LLMs 👏👀
mlx-vlm v0.0.4 is here 🎉
New models 🤖:
- Idefics 2
- Llava (Phi and Llama 3)
Improvements 🚀:
- Q4 quantisation support for all models
- Less imports to use generate()
Up next 🚧:
- More models
- Support for multiple images
Please leave us a star and send a PR
These findings 👇 on (1) reliability in news articles and (2) in the language models application for generating writer ✍️ feedback generation from the angle of readers 👀📃 view through personalities" are 💎 to skim.
Excited for our
#CHI2024
contributions (1/2):
Reliability Criteria for News Websites, 16 May, 11:30am
Writer-Defined AI Personas for On-Demand Feedback Generation, 15 May, 2:00pm
#CAISontour
It is nice too see a small step towards the target-oriented LLM adaptation from the prospect of retrieval augmenting techniques and enhanced end-to-end adaptation of 🥞: (I) knowledge (ii) passages (iii) LLM
Today, we’re excited to announce RAG 2.0, our end-to-end system for developing production-grade AI.
Using RAG 2.0, we’ve created Contextual Language Models (CLMs), which achieve state-of-the-art performance on a variety of industry benchmarks. CLMs outperform strong RAG
Text2Story workshop opener at
#ecir2024
shares a handy methodology aligned studies for processing large texts such as books 📚 aimed at narratives extraction
#nlp
#story
#books
#narratives
@alan_karthi
Well done and thank you for sharing this technical report! 👏 I believe that the access to the Med-Gemini is restricted due to the specifics for the medical domain as well as the result LLM. Nonetheless, is Med-Gemini available for chatting and under which license of so?
📢 Excited to share the details of our submission🥉
@SemEvalWorkshop
Track-3, which is based on CoT reasoning 🧠 with Flan-T5 🤖, as a part of self-titled nicolay-r 📜. Due to remote avalablity at
#NAACL2024
, presenting it by breaking down the system highlights here 👇
🧵1/n
The most recent OmniFusion VLLM in which authors adopt merging-features for CLIP-ViT-L and DINOv2 was such an impressive 🔥 and powered by Mistral-7B. This makes me wonder, how far the another 💎 concept for images encoding 👇that involves MoE goes ... 👀
it's raining vision language models ☔️
CuMo is a new vision language model that has MoE in every step of the VLM (image encoder, MLP and text decoder) and uses Mistral-7B for the decoder part 🤓
[1/7] 🚀 Introducing the Language Model Transparency Tool - an open-source interactive toolkit for analyzing Transformer-based language models.
We can't wait to see how the community will use this tool!
@drivelinekyle
@abacaj
This template varies from task to task, but the impelementation on torch is pretty much is similar.
My personal experience is sentiment analysis, so I can recommend:
🤔 Coming to this from the prospect of IR from large textual data, becoming wondered on how it would be interesting to see such a forecasting for extracted stories (series of events) from literature novel books 📚
📢New LLM Agents Benchmark!
Introducing 🌟MIRAI🌟: A groundbreaking benchmark crafted for evaluating LLM agents in temporal forecasting of international events with tool use and complex reasoning!
📜 Arxiv:
🔗 Project page:
🧵1/N
📢Research presentation alert🚨
Nearly in 20 days ready to share personal findings in LLMs application for reasoning 🧠 in sentiment analysis task. Inviting everyone to my talk, feel free to join the the event 🙌
Useful links:
⭐️
📜
It was always encouraging to see how high academia compete in scientific advances, while even more amazing to see that in sports! 🔥 💪 💪 💪 🚣♀️ 🚣♂️ 🛶
Yes, and nowadays it is still possible to see such traninings at Hammersmith quayside in London! 🔥
@SemEvalWorkshop
our 🛠️ reforged 🛠️ version of the THoR which has:
✅1. Adapted prompts for Emotions Extraction
✅2. Implemented Reasoning-Revision 🧠
✅3. GoogleColab launch notebook (details in further posts 🧵)
⭐️Github:
🧵 4/n
#NAACL2024
@yufanghou
Thanks! By being not physically at
#NAACL2024
this year, rather remotely at
#SemEval
, finding it 💎 a quick poster skimming from the Summary Content Units as well as semantical tree construction for the textual content 👀
During last few years the importance of quick transoformer tunings for downstream tasks become even more demanded. Earlier announced awesome list of sentiment analysis papers has been enlarged with recent advances in more time-effective tuning techniques
One of the inspirative directions (Dimension) of narrative in long texts that were highlighted at
#ecir2024
#Text2Story
is Spacial 🌎🗺️ ...
Further details on pipeline and timeline tracking ...
🧵[1/3]
@shaily99
Handy to go with Overleaf + DrawIO for concept diagrams. For the overleaf, forming "lastest.tex" 📝 which later become renamed to specific date, so that becomes a 📑 eventually, which could be gathered into "main.tex"
Managing attitudes of a single texts Is not the only option available in AREkit (). We are also consider a laaaa...aaarge scale collections of texts with relations, and a way of how such collections could be handled by AREkit. Stay tuned)
#arekit
#nlp
Thanks for the provided opportunity to Huizhi Liang and for all students who got an opportunity to attend on the first guest lecture at Newcasle University! 🎉🎉🎉 The presentation was devoted to advances in sentiment attitude extraction
#newcastle
#ml
#nlp
#arekit
#lecture
Catch me to find out more on how ARElight may be applied for your large texts 📚/ 📰 @
#ecir2024
demo track 📜💻. Thanks to my
@UniofNewcastle
colleagues: Huizhi Liang, Maxim Kalameyets,
@lshi_ncl
for work on system✨📺
📍lobby poster / demo session
#nlp
#lm
#ir
#sampling
📢 I am happy to share that our studies made at
@UniofNewcastle
, aimed at fictional character personality extraction from literature novel books 📚, by solely rely on ⚠️ book content⚠️, become ACCEPTED at
#LOD2024
@ Toscana, Italy 🇮🇹 🎉
👨💻:
🧵1/n
Google presents Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
1B model that was fine-tuned on up to 5K sequence length passkey instances solves the 1M length problem
Can we teach Transformers Causal Reasoning?
We propose Axiomatic Framework, a new paradigm for training LMs. Our 67M-param model, trained from scratch on simple causal chains, outperforms billion-scale LLMs and rivals GPT-4 in inferring cause-effect relations over complex graphs
@mudler_it
@LocalAI_API
Thanks for such a verbose explanation on the related differences! I believe I have to first find out more about function calling 👀
🚨 New LLM personalization/alignment paper 🚨
🤔 How can we obtain personalizable LLMs without explicitly re-training reward models/LLMs for each user?
✔ We introduce a new zero-shot alignment method to control LLM responses via the system message 🚀
💎 Fact checking domain and advances in it are important for performing IR from news, and mass-media. These advances may serve with the new potential approaches aimed at enhancing LLMs reasoning capabilities in author opinion mining / Sentiment Analysis ✨
Refine LLM responses to improve factuality with our new three-stage process:
🔎Detect errors
🧑🏫Critique in language
✏️Refine with those critiques
DCR improves factuality refinement across model scales: Llama 2, Llama 3, GPT-4.
w/
@lucy_xyzhao
@jessyjli
@gregd_nlp
🧵
📊Results of the gpt-4o (zero-shot) reasoning in Sentiment Analysis on English and non-English texts.
Surprised to find low F1 results ⏬in English, while multilingual capabilities (ru) are still at the top levels 👑
#gpt4o
#reasnoning
#nlp
#zsl
#sentimetnalalysis
#benchmark
Long Context LLMs Struggle with Long In-Context Learning
Finds that after evaluating 13 long-context LLMs on long in-context learning the LLMs perform relatively well under the token length of 20K. However, after the context window exceeds 20K, most LLMs except GPT-4 will dip
@JLopez_160
@cohere
Thank you for sharing this, interesting to see how it goes with LLMs 👏👀 Legal documents are tend to be long in length, so how specifically you sample them?
Just released new information extraction models: lora weights trained on Meta-Llama-3-8B-Instruct with IEPile corpus, and a full-parameter fine-tuned information extraction model, OneKE, based on Chinese-Alpaca-2-13B for the community! 🚀
#OpenSource
#ModelWeights
#IEPile
#NLP
📢 Calling all
#NLProc
enthusiasts! The Shared Task on Perspective
#ArgumentRetrieval
is open for registration. Join us in this exciting challenge & develop methods to tailor arguments to different audiences!
📭
(1/🧵)
#argmining_2024
#ACL2024NLP
📢 Taking a look on to reasoning prospects of LLMs in linguistic tasks, it is necessary to go with data in English! Here is my findings on 📊 comparison in LLM reasoning between data written in:
☑ English
✅ Non-english (Russian)
Reasoning capabilities by F1(PN) are tend to be