←
Negar Arabzadeh558 posts
Negar Arabzadeh avatar

Negar Arabzadeh

@NegarEmpr

Postdoc @UCBerkeley @BerkeleySky |👩🏻‍💻Prev @google, @MSFTResearch, @SpotifyResearch | 📚@UWaterloo | Interested in Information Retrieval

◷ Joined April 2017▧ 86 Photos and videos
Negar Arabzadeh avatar
Negar Arabzadeh@NegarEmpr·Jul 23

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

Post attachmentPost attachmentPost attachment
Niloofar avatar
⟳ Negar Arabzadeh retweeted
Niloofar@niloofar_mire·Nov 10

“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

Negar Arabzadeh avatar
Negar Arabzadeh@NegarEmpr·Oct 25

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 🧵

Post attachment
Negar Arabzadeh avatar
Negar Arabzadeh@NegarEmpr·Oct 23

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 🔥

Negar Arabzadeh avatar
Negar Arabzadeh@NegarEmpr·Oct 23

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.

Post attachment
Negar Arabzadeh avatar
Negar Arabzadeh@NegarEmpr·Oct 23

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.

Post attachment
Negar Arabzadeh avatar
Negar Arabzadeh@NegarEmpr·Oct 23

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.

Post attachment
Haolun Wu avatar
⟳ Negar Arabzadeh retweeted
Haolun Wu@Haolun_Wu0203·Oct 18

📢 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

Post attachment
Negar Arabzadeh avatar
Negar Arabzadeh@NegarEmpr·Oct 16

Excited to be co-organizing our Trust4RSI-Agent Workshop at #AAAI2027 ! A Workshop on Trustworthy Evolution of AI Agents! 🚀 🥳We have an amazing lineup of speakers and panelists: @Yoshua_Bengio , @MengdiWang10 , @du_yilun , @hugo_larochelle , @ZheqingZhu , and @__yuezhao__ ! 📝 Submission deadline: November 20, 2026 📬 Author notification: December 2, 2026 📍 February 22–23, 2027 · Montréal, Canada 🌐 trust4rsi-agent.github.io/AA… Please share with colleagues working in this space and looking forward to your submissions! Happy to be organizing this alongside @Haolun_Wu0203 @HuaWenyue31539 @BangL93 @lcharlin! #AAAI2027 #AIAgents

Post attachment
Negar Arabzadeh avatar
Negar Arabzadeh@NegarEmpr·Oct 8

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! 🙌

Post attachment
Negar Arabzadeh avatar
Negar Arabzadeh@NegarEmpr·Oct 8

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

Danny To Eun Kim avatar
⟳ Negar Arabzadeh retweeted
Danny To Eun Kim@TEKnologyy·Oct 7

Agent Swarms are scaling to 1000+ agents, and your message board gets congested. Who builds search for them? #COLM2026 📍Lifelong Agent workshop (Friday)

Post attachment
Negar Arabzadeh avatar
Negar Arabzadeh@NegarEmpr·Oct 5

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

Shengyao Zhuang avatar
⟳ Negar Arabzadeh retweeted
Shengyao Zhuang@ShengyaoZhuang·Sep 19

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.

Post attachment