Max Conti (@mlpc123) header
Max Conti (@mlpc123) profile picture

Research in NLP @illuintech, CS MSc @epfl

Paris
Joined September 2024
Photo by Max Conti (@mlpc123)Photo by Max Conti (@mlpc123)Photo by Max Conti (@mlpc123)Photo by Max Conti (@mlpc123)Photo by Max Conti (@mlpc123)Photo by Max Conti (@mlpc123)Photo by Max Conti (@mlpc123)Photo by Max Conti (@mlpc123)Photo by Max Conti (@mlpc123)Photo by Max Conti (@mlpc123)
Max Conti retweeted
🏛️ LLM agents in a new environment repeat the same mistakes. Meet DAEDALUS: agent memory bootstrapped from tasks the agent writes itself, with no training tasks or human-written guidelines. It makes 7 agents from various model families succeed more often, in fewer turns 🧵⬇️
4
5
5
27
1,985
Our latest work at @illuintech is out! 🕺 DAEDALUS is a training-free pipeline that generates priors on any new environment, that an agent can use in-context at test time. No tasks/verifier/human-written guidelines required! Details and fav take-aways in the thread below 👇 (1/n)
1
3
11
362
This post would not be complete without an enormous thanks to the amazing team that made this project possible but most importantly really fun @antoine_edy, @victortxing, @marcantallard, @Nawfal_BENH and Gautier! 🫶 And for the unconditional support @MaceQuent1 🤝 (9/9)
1
3
69
Doing an agentic project was definitely not an easy task and we discovered a lot of new challenges, including some that we would love to keep digging into. Let us know what you think of the result, we're happy to hear about your thoughts and discuss!
2
75
Love the blog's title, nice wink at our work with @mlpc123 ! More importantly, I love the content ! Contextual embeddings is a super high potential direction with lots to do! Still waiting on 1M context window parallel embeddings though @antoine_chaffin @bo_wangbo 😘
We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view. pplx-embed-v2-context-9b-preview sets a new state of the art on ConTEB and @turbopuffer's new, privately held context-bench. perplexity.ai/hub/blog/conte…
3
2
17
1,544
Max Conti retweeted
I will be in Seoul with @marcantallard this week for ICML to present ModernVBERT 🇰🇷 Our poster session on Wednesday from 10:30PM in Hall A (#4104). Come chat with us!
Introducing ModernVBERT: a vision-language encoder that matches the performance of models 10× its size on visual document retrieval tasks! 👁️ Read more in the thread👇 (1/N)
4
1
14
1,661
Max Conti retweeted
if you write some really good code these days everyone thinks you did it with Claude Code. if you lose a lot of weight everyone thinks you did it with Ozempic. at least you can still be really good at dancing. they don't make ozempic or Claude Code for being good at dancing
40
58
9
1,364
31,312
Max Conti retweeted
okay maybe it's a good time? We have a small colbert model trained at pplx, it is a continue-training of pplx-embed-0.6b, so native multilingual, just made it open and added a section how to use MaxSim kernel: huggingface.co/perplexity-ai…
Releasing my first kernel on @huggingface: MaxSim Late-interaction retrieval (ColBERT / PyLate) bottlenecks on materializing the full similarity matrix. This kernel avoids it by using tiled scoring with simdgroup_matrix (Metal) and WMMA. Result is 3–5× speedup compared to naive PyTorch. Try it out 👇
7
17
3
97
24,684
Exciting publication alert!! Congrats to the whole team for the nice ideas and thorough execution 🎯 Hyped to take the time to deep-dive into every part :)
🚨 Do LLMs need to store everything they read in memory? To reduce KV cache size and improve decoding speeds, we propose Self-Pruned KV attention, a mechanism where the model learns to decide which KVs to write in the persistent KV cache, discarding all the rest! @AIatMeta🧵
2
114
We're releasing LateOn and DenseOn today. Two open retrieval models, 149M parameters each. LateOn (ColBERT, multi-vector): 57.22 NDCG@10 on BEIR. DenseOn (dense, single-vector): 56.20. Both beat models up to 4× larger We're open-sourcing the weights under Apache 2.0 🧵👇
2
27
2
166
10,000
The new generation of open state-of-the-art single and multi-vector retrieval models is here It's time, DenseOn with the LateOn 🎶 @LightOnIO releases models that leap past existing ones, and everything you need to do the same!
15
53
16
233
53,080
Max Conti retweeted
Update on the Late-Interaction Workshop @ ECIR2026: it was amazing! 🇳🇱 So cool to meet late-interactors IRL for the first time, I enjoyed every bit of that day 🤗 And congrats & huge thanks to the organizers again. Link to our work + poster below ⬇️
3
8
34
3,158
Looking forward to meeting fellow late interactors! 🤓🇳🇱
Replying to @mlpc123
@mlpc123, @MaceQuent1 and I will be at the Late Interaction Workshop at #ECIR2026 on Thursday 🤗 See you in Delft 🇳🇱
1
73