So excited to share that I received the SIGIR Early Career Research Award! 🥹
I still remember attending my first SIGIR, watching someone receive this award, and thinking, “There’s no way that could ever be me.” And now, here I am!😵
This truly means so much to me. Thank you to the @ACMSIGIR community for recognizing my contributions. #SIGIR2026
P.S. Get yourself a PhD supervisor who matches your award-celebration energy 😄 So cool to celebrate this moment together! @claclarke
“The third world makes very little contribution to science” is SUCH A FALSE statement!!! Do u know how many of the top ai researchers in these institutions u are crediting so much come from third world countries and did their undergrads there?? U cant conflate things this much
I'll be at #EMNLP2026 in Budapest this week! 🎉 🇭🇺
Presenting "RAG over Thinking Traces Can Improve Reasoning Tasks" today at 11 AM
📍Poster Session A, Hall H.
Come say hi! happy to chat about reasoning, RAG, and everything in between!
1/ Thrilled to introduce T³: a corpus for RAG over reasoning tasks, built from thinking traces.
We show that surprisingly RAG can improve reasoning— with the right corpus.
Rag with Transformed Thinking Traces T³ gain by up to 43.9% on AIME 2025-2026.
🔗 arxiv.org/abs/2605.03344 🧵
4/ We evaluated FLINT with different backbones on general retrieval benchmarks like BEIR and more complex retrieval tasks in BrowseComp+, TREC Tip-of-the-Tongue, and CRUMB. we also explored impact of vector budgets of 16, 32, and 64.
📄 Paper: arxiv.org/abs/2610.27273
💻 Code: github.com/hmk55555/FLINT
🤗 Models: huggingface.co/collections/h…
Huge thanks to @matei_zaharia and especially @HimankHanda for leading this work 🔥
3/ How does FLINT compare with other retrievers?
With ModernBERT and 32 vectors per query and document:
🎯 Higher average ranking quality than the single-vector bi-encoder on every benchmark suite, with especially large gains on complex queries.
⚡ Higher average ranking quality than ConstBERT on every suite, with 1.5–2.7× faster retrieval on the evaluated long-query corpora.
💾 Nearly matching ColBERTv2 on BEIR and outperforming it on CRUMB, with much smaller indexes.
Single-vector retrieval remains faster and more compact. FLINT offers a middle ground: richer matching with a fixed vector budget.
2/ Since ColBERT keeps one vector per token, storage and search costs grow with the number of tokens.
On the other hand, FLINT represents every query and document with a fixed number of vectors.
A small set of learned vectors attends over the token embeddings and pools them into V vectors. We then use the same MaxSim scoring as ColBERT.
FLINT pools both queries and documents, so longer text can change what the vectors capture without increasing their number.
1/ 💰Multi-vector retrieval shouldn’t charge you by the token!
🎉 Excited to share FLINT (Fixed-budget Late INTeraction), a late-interaction retriever designed for long, complex queries with up to 89% reduction in index and 23-170× faster retrieval latency.⚡
🎛️ FLINT gives a vector-budget knob to balance storage, latency, and quality.
📄 Paper: arxiv.org/abs/2610.27273
How does it work? 🧵
ColBERT stores and compares one vector per token. FLINT pools every query and every document into a fixed number of vectors, so there’s far less to store and far fewer comparisons at search time.
📢 𝗔𝗔𝗔𝗜 𝟮𝟬𝟮𝟳 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗣𝗮𝗽𝗲𝗿𝘀
𝗧𝗿𝘂𝘀𝘁𝘄𝗼𝗿𝘁𝗵𝘆 𝗘𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻 𝗼𝗳 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀: 𝘼𝙣 𝘼𝙜𝙚𝙣𝙩 𝙊𝙥𝙚𝙧𝙖𝙩𝙞𝙣𝙜 𝙎𝙮𝙨𝙩𝙚𝙢 𝙋𝙚𝙧𝙨𝙥𝙚𝙘𝙩𝙞𝙫𝙚
📍 𝗣𝗮𝗹𝗮𝗶𝘀 𝗱𝗲𝘀 𝗖𝗼𝗻𝗴𝗿𝗲̀𝘀, 𝗠𝗼𝗻𝘁𝗿𝗲́𝗮𝗹, 𝗖𝗮𝗻𝗮𝗱𝗮 🇨🇦
🗓️ 𝗙𝗲𝗯𝗿𝘂𝗮𝗿𝘆 𝟮𝟮–𝟮𝟯, 𝟮𝟬𝟮𝟳 (one-day workshop, exact day TBA)
AI agents now continuously evolve. How do we keep them trustworthy?
💡 𝗪𝗵𝘆 𝗮 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 𝗽𝗿𝗼𝗯𝗹𝗲𝗺?
Many failures come not from a broken model, but from a bad memory, an over-privileged tool, or an update that cannot be undone. Operating systems 🖥️ solved this long ago. We bring that lens to agents, making their evolution 𝘁𝗿𝗮𝗰𝗲𝗮𝗯𝗹𝗲, 𝗯𝗼𝘂𝗻𝗱𝗲𝗱, 𝗮𝗻𝗱 𝗿𝗲𝘃𝗲𝗿𝘀𝗶𝗯𝗹𝗲 🛡️
📌 𝗧𝗼𝗽𝗶𝗰𝘀
🧠 𝗠𝗲𝗺𝗼𝗿𝘆 (File systems): provenance, isolation, rollback
🛠️ 𝗧𝗼𝗼𝗹𝘀 & 𝗦𝗸𝗶𝗹𝗹𝘀 (Permissions): least privilege, sandboxing, revocation
📈 𝗠𝗼𝗱𝗲𝗹𝘀 & 𝗣𝗼𝗹𝗶𝗰𝗶𝗲𝘀 (System updates): versioning, no silent alignment drift
🤝 𝗠𝘂𝗹𝘁𝗶-𝗔𝗴𝗲𝗻𝘁 (Process isolation): stop one failure from spreading
📊 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 (Logging): trace every failure to the change behind it
🎤 𝗦𝗽𝗲𝗮𝗸𝗲𝗿𝘀 & 𝗣𝗮𝗻𝗲𝗹𝗶𝘀𝘁𝘀: @Yoshua_Bengio (UdeM, LawZero, Mila), @MengdiWang10 (Princeton), @du_yilun (Harvard), @hugo_larochelle (Mila), @ZheqingZhu (Pokee AI), and @yzhao010 (USC).
⏰ 𝗞𝗲𝘆 𝗗𝗮𝘁𝗲𝘀 & 𝗦𝘂𝗯𝗺𝗶𝘀𝘀𝗶𝗼𝗻
📝 Submission deadline: Nov 20, 2026 (AoE)
📬 Author notification: Dec 2, 2026 (AoE)
- Full papers: 8 pages; Short / position papers: 4 pages
- Double-blind review, AAAI format
🔗 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗪𝗲𝗯𝘀𝗶𝘁𝗲: trust4rsi-agent.github.io/AA…
📝 𝗣𝗮𝗽𝗲𝗿 𝗦𝘂𝗯𝗺𝗶𝘀𝘀𝗶𝗼𝗻: openreview.net/group?id=AAAI…
📢 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗲𝗱 𝗶𝗻 𝗯𝗲𝗰𝗼𝗺𝗶𝗻𝗴 𝗮 𝘄𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝘀𝗽𝗼𝗻𝘀𝗼𝗿? Contact us at trust4rsi.agent@gmail.com
Happy to organize with @NegarEmpr, @HuaWenyue31539, @BangL93, and @lcharlin.
Big thanks to the support and advisory from @StevenYuan666, Yankai Chen, Tianyu Shi, @BokwaiHo, @preslav_nakov, Steve Liu, @alex_pentland
We look forward to seeing you in Montréal! 🇨🇦
#AAAI2027#AIAgents#TrustworthyAI#AISafety#LLM#CallForPapers
Had a great time presenting DeepScholar-Bench at #COLM2026 today! Lots of interesting conversations and interactions! 🤩
If you’re building a deep research system, give our benchmark a try!
@COLM_conf has been such an engaging and fun conference so far! 🙌
Today at #COLM2026 I will present DeepScholar-Bench and how we can evaluate AI-generated research synthesis!
📍 Imperial Ballroom, Poster #72
🕚 Today, 11 AM–1 PM
Come stop by! Would love to chat!
I'll be BARTing over to #COLM2026 this week 🚇😄
Around all week and happy to chat about search agents & deep research systems!
📄 Thu: DeepScholar-Bench
arxiv.org/abs/2508.20033
📄 Fri: Multi-Agent Transactive Memory @ Lifelong Agents Workshop
arxiv.org/abs/2606.19911
Agent Swarms are scaling to 1000+ agents, and your message board gets congested. Who builds search for them? #COLM2026
📍Lifelong Agent workshop (Friday)
I'll be BARTing over to #COLM2026 this week 🚇😄
Around all week and happy to chat about search agents & deep research systems!
📄 Thu: DeepScholar-Bench
arxiv.org/abs/2508.20033
📄 Fri: Multi-Agent Transactive Memory @ Lifelong Agents Workshop
arxiv.org/abs/2606.19911
For IR folks: @xueguang_ma and I quickly tested Jev as a pointwise/pairwise/setwise/listwise reranker on the classic DL19 and DL20, reranking the top 100 BM25 results. It is pretty good and cheap.