Anmol Kabra
@anmolkabra.com
anmolkabra.com
ML PhD at @cornellbowers.bsky.social: LLM reasoning, agents, and AI for Science. Can cycle, run, juggle. Currently trying combinations.
ML PhD at @cornellbowers.bsky.social: LLM reasoning, agents, and AI for Science. Can cycle, run, juggle. Currently trying combinations.
Presenting PhantomWiki with @albertgong.bsky.social and Johann at @icmlconf.bsky.social on Tuesday 11am + an oral talk at Long Context Workshop on Saturday! Come say hi/chat about LLM reasoning and retrieval evaluation!
July 14, 2025 at 9:33 PM
Presenting PhantomWiki with @albertgong.bsky.social and Johann at @icmlconf.bsky.social on Tuesday 11am + an oral talk at Long Context Workshop on Saturday! Come say hi/chat about LLM reasoning and retrieval evaluation!
🚨 Our paper PhantomWiki is accepted to ICML 2025
@icmlconf.bsky.social
OG: bsky.app/profile/anmo...
🧑💻We designed it as a future-proof LLM reasoning benchmark. And it shows: new Qwen3-32B model with auto-thinking-mode struggles with higher difficulty questions, like DeepSeek-R1 from Jan
@icmlconf.bsky.social
OG: bsky.app/profile/anmo...
🧑💻We designed it as a future-proof LLM reasoning benchmark. And it shows: new Qwen3-32B model with auto-thinking-mode struggles with higher difficulty questions, like DeepSeek-R1 from Jan
June 10, 2025 at 7:47 PM
🚨 Our paper PhantomWiki is accepted to ICML 2025
@icmlconf.bsky.social
OG: bsky.app/profile/anmo...
🧑💻We designed it as a future-proof LLM reasoning benchmark. And it shows: new Qwen3-32B model with auto-thinking-mode struggles with higher difficulty questions, like DeepSeek-R1 from Jan
@icmlconf.bsky.social
OG: bsky.app/profile/anmo...
🧑💻We designed it as a future-proof LLM reasoning benchmark. And it shows: new Qwen3-32B model with auto-thinking-mode struggles with higher difficulty questions, like DeepSeek-R1 from Jan
Brilliant work at @cornelluniversity.bsky.social with @albertgong.bsky.social, Chao, @kamile.st, Raphael, Johann, JT, Carla Gomes, and @kilianqw.bsky.social!
Paper on arxiv: 📄 arxiv.org/abs/2502.20377
Paper on arxiv: 📄 arxiv.org/abs/2502.20377
March 5, 2025 at 8:05 PM
Brilliant work at @cornelluniversity.bsky.social with @albertgong.bsky.social, Chao, @kamile.st, Raphael, Johann, JT, Carla Gomes, and @kilianqw.bsky.social!
Paper on arxiv: 📄 arxiv.org/abs/2502.20377
Paper on arxiv: 📄 arxiv.org/abs/2502.20377
PhantomWiki generates datasets of wiki pages and reasoning questions about the universe of people, on the scale of Wikipedia 🌐
🚨The universe of people and their relationships are generated randomly. So by construction, LLMs cannot memorize/cheat on PhantomWiki evaluation.
🚨The universe of people and their relationships are generated randomly. So by construction, LLMs cannot memorize/cheat on PhantomWiki evaluation.
March 5, 2025 at 8:05 PM
PhantomWiki generates datasets of wiki pages and reasoning questions about the universe of people, on the scale of Wikipedia 🌐
🚨The universe of people and their relationships are generated randomly. So by construction, LLMs cannot memorize/cheat on PhantomWiki evaluation.
🚨The universe of people and their relationships are generated randomly. So by construction, LLMs cannot memorize/cheat on PhantomWiki evaluation.
🚀 📢 Releasing PhantomWiki, a reasoning + retrieval benchmark for LLM agents!
If I asked you "Who is the friend of father of mother of Tom?", you'd simply look up Tom -> mother -> father -> friend and answer.
🤯 SOTA LLMs, even DeepSeek-R1, struggle with such simple reasoning!
If I asked you "Who is the friend of father of mother of Tom?", you'd simply look up Tom -> mother -> father -> friend and answer.
🤯 SOTA LLMs, even DeepSeek-R1, struggle with such simple reasoning!
March 5, 2025 at 8:05 PM
🚀 📢 Releasing PhantomWiki, a reasoning + retrieval benchmark for LLM agents!
If I asked you "Who is the friend of father of mother of Tom?", you'd simply look up Tom -> mother -> father -> friend and answer.
🤯 SOTA LLMs, even DeepSeek-R1, struggle with such simple reasoning!
If I asked you "Who is the friend of father of mother of Tom?", you'd simply look up Tom -> mother -> father -> friend and answer.
🤯 SOTA LLMs, even DeepSeek-R1, struggle with such simple reasoning!