Sign in

a-krishnan.bsky.social

@a-krishnan.bsky.social
46 followers 68 following 8 posts

Master student at Saarland university

PostsRepliesMedia
Reposted by @a-krishnan.bsky.social
ncg @n.grnfld.me · 17/07/2026
Back from Seoul. My first paper, "An Isotropic Approach to Efficient UQ with Gradient Norms", got a poster and an oral at ProbML, and came away with the Best Paper Award. Still a bit stunned. arxiv.org/abs/2603.29466
1142
a-krishnan.bsky.social @a-krishnan.bsky.social · 26/10/2025
Join me and @mariusmosbach.bsky.social to chat about our work on frequency effects in unlearning — and how @ai2.bsky.social's Olmo helped us gain key insights. 💬 AMA: Tue, Oct 28 — 8:00 PT / 16:00 CEST 💡 Bring your questions! 🔗 discord.gg/ai2
discord.gg
Join the Ai2 Discord Server!
The official Discord for Ai2 (The Allen Institute for AI), a nonprofit AI lab. | 2491 members
020
a-krishnan.bsky.social @a-krishnan.bsky.social · 05/10/2025
We're presenting “Not all data are unlearned equally” at #COLM2025! We show that data properties shape how LLMs forget — stop by to chat more! 🗓 Wednesday, Oct 8 🕓 4:30–6:30 pm 📍 poster #710 (session 4) paper: arxiv.org/abs/2504.05058 Work with @mariusmosbach.bsky.social @sivareddyg.bsky.social
arxiv.org
Not All Data Are Unlearned Equally
Machine unlearning is concerned with the task of removing knowledge learned from particular data points from a trained model. In the context of large language models (LLMs), unlearning has recently re...
000
Reposted by @a-krishnan.bsky.social
Benno Krojer @bennokrojer.bsky.social · 13/08/2025
very happy to see the trend of a Behind the Scenes section catching on! transparent & honest science 👌 love the detailed montreal spots mentioned consider including such a section in your next appendix! (paper by @a-krishnan.bsky.social arxiv.org/pdf/2504.050...)
181
Reposted by @a-krishnan.bsky.social
Gaurav Kamath @grvkamath.bsky.social · 29/07/2025
Our new paper in #PNAS (bit.ly/4fcWfma) presents a surprising finding—when words change meaning, older speakers rapidly adopt the new usage; inter-generational differences are often minor. w/ Michelle Yang, ‪@sivareddyg.bsky.social‬ , @msonderegger.bsky.social‬ and @dallascard.bsky.social‬👇(1/12)
33317
a-krishnan.bsky.social @a-krishnan.bsky.social · 30/07/2025
📢 #SpeechTech & #SpeechScience researchers! We are thrilled to announce that Prof. Karen Livescu will keynote our Special Session on Interpretable Audio and Speech Models at #Interspeech2025: "What can interpretability do for us (and what can it not)?" 🗓️ Aug 18, 11:00 @interspeech.bsky.social
sites.google.com
Announcements
Keynote Speaker Announcement 🔊 30.07.2025 We are delighted to announce the keynote speech t`hat will happen at the special session! Speaker: Prof. Karen Livescu, Toyota Technological Institute at Ch...
041
Reposted by @a-krishnan.bsky.social
Gaofei Shen @gaofeishen.com · 26/05/2025
I am excited to announce that my paper "On the reliability of feature attribution methods for speech classification" has been accepted to #Interspeech2025! Co-authors: @hmohebbi.bsky.social, Arianna Bisazza, Afra Alishahi, @grzegorz.chrupala.me Find the preprint here: arxiv.org/abs/2505.16406
arxiv.org
On the reliability of feature attribution methods for speech classification
As the capabilities of large-scale pre-trained models evolve, understanding the determinants of their outputs becomes more important. Feature attribution aims to reveal which parts of the input elemen...
1102
Reposted by @a-krishnan.bsky.social
Vagrant Gautam @dippedrusk.com · 03/05/2025
Come to my keynote tomorrow at the first official @queerinai.com workshop at #NAACL2025 to hear about how trans languaging is complex and cool, and how this makes it extra difficult to process computationally. I will have SO many juicy examples!
Title slide: Processing Trans Languaging - Vagrant Gautam (they/xe), Saarland University, with a very brightly patterned background featuring colourful people and math symbols.
34414
Reposted by @a-krishnan.bsky.social
Michael Hahn @m-hahn.bsky.social · 05/05/2025
Chain-of-Thought (CoT) reasoning lets LLMs solve complex tasks, but long CoTs are expensive. How short can they be while still working? Our new ICML paper tackles this foundational question.
2122
Reposted by @a-krishnan.bsky.social
Benno Krojer @bennokrojer.bsky.social · 01/05/2025
A must-read for anyone in NLP right now
161
Reposted by @a-krishnan.bsky.social
Mila - Institut québécois d'IA @mila-quebec.bsky.social · 01/05/2025
Congratulations to Mila members @adadtur.bsky.social , Gaurav Kamath and @sivareddyg.bsky.social for their SAC award at NAACL! Check out Ada's talk in Session I: Oral/Poster 6. Paper: arxiv.org/abs/2502.05670
0137
Reposted by @a-krishnan.bsky.social
Siva Reddy @sivareddyg.bsky.social · 01/05/2025
Incredibly proud of my students @adadtur.bsky.social and Gaurav Kamath for winning a SAC award at #NAACL2025 for their work on assessing how LLMs model constituent shifts.
arxiv.org
Language Models Largely Exhibit Human-like Constituent Ordering Preferences
Though English sentences are typically inflexible vis-à-vis word order, constituents often show far more variability in ordering. One prominent theory presents the notion that constituent ordering is ...
1175
Reposted by @a-krishnan.bsky.social
Yanai Elazar @yanai.bsky.social · 25/04/2025
💡 New ICLR paper! 💡 "On Linear Representations and Pretraining Data Frequency in Language Models": We provide an explanation for when & why linear representations form in large (or small) language models. Led by @jackmerullo.bsky.social, w/ @nlpnoah.bsky.social & @sarah-nlp.bsky.social
34212
Reposted by @a-krishnan.bsky.social
Xing Han Lu @xhluca.bsky.social · 12/04/2025
DeepSeek-R1 Thoughtology: Let’s <think> about LLM reasoning 142-page report diving into the reasoning chains of R1. It spans 9 unique axes: safety, world modeling, faithfulness, long context, etc. Now on arxiv: arxiv.org/abs/2504.07128
161
Reposted by @a-krishnan.bsky.social
Xing Han Lu @xhluca.bsky.social · 15/04/2025
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories We are releasing the first benchmark to evaluate how well automatic evaluators, such as LLM judges, can evaluate web agent trajectories.
174
Reposted by @a-krishnan.bsky.social
Marius Mosbach @mariusmosbach.bsky.social · 16/04/2025
Checkout Benno's notes about our impact of interpretability paper 👇. Also, we are organizing a workshop at #ICML2025 which is inspired by some of the questions discussed in the paper: actionable-interpretability.github.io
actionable-interpretability.github.io
General Information
ICML 2025 - Vancouver
0113
Reposted by @a-krishnan.bsky.social
Marius Mosbach @mariusmosbach.bsky.social · 09/04/2025
Check out our new paper on unlearning for LLMs 🤖. We show that *not all data are unlearned equally* and argue that future work on LLM unlearning should take properties of the data to be unlearned into account. This work was lead by my intern @a-krishnan.bsky.social 🔗: arxiv.org/abs/2504.05058
Diagram illustrating a hypothesis about knowledge unlearning in language models. The left side shows a training corpus with varying frequencies of facts, such as 'Montreal is a city in Quebec' (high frequency) and 'Atlantis is a city in the ocean' (lower frequency). The center shows a language model being trained on this data, then undergoing unlearning. The right side demonstrates the 'Forget Quality' results, where the model more effectively unlearns the less frequent fact ('Atlantis is in Greece') while retaining the more frequent knowledge. Labels A, B, and C mark key points in the hypothesis: A (frequency variations in training data), B (influence of frequency), and C (unlearning effectiveness).
1325
Reposted by @a-krishnan.bsky.social
MAPS - CVPR 2026 Workshop @mapscvpr.bsky.social · 14/03/2025
📢Excited to announce our upcoming workshop - Vision Language Models For All: Building Geo-Diverse and Culturally Aware Vision-Language Models (VLMs-4-All) @CVPR 2025! 🌐 sites.google.com/view/vlms4all
11711
Reposted by @a-krishnan.bsky.social
Xing Han Lu @xhluca.bsky.social · 10/03/2025
Agents like OpenAI Operator can solve complex computer tasks, but what happens when users use them to cause harm, e.g. spread misinformation? To find out, we introduce SafeArena (safearena.github.io), a benchmark to assess the capabilities of web agents to complete harmful web tasks. A thread 👇
1167
a-krishnan.bsky.social @a-krishnan.bsky.social · 01/02/2025
📢 #SpeechTech & #SpeechScience researchers! ⏳ Reminder: The #Interspeech2025 deadline is approaching! 🚀 If your work focuses on interpretability in speech & audio, submit through our Special Session and showcase your research! 🎤 #Interpretability @interspeech.bsky.social
sites.google.com
Home
Introduction Audio and speech technology has recently achieved unprecedented success in real-world applications, driven primarily by self-supervised pre-training of large neural networks on massive da...
110