Tongxuan Liu, et al.: xLLM Technical Report https://arxiv.org/abs/2510.14686 https://arxiv.org/pdf/2510.14686 https://arxiv.org/html/2510.14686
October 17, 2025 at 6:30 AM
Tongxuan Liu, et al.: xLLM Technical Report https://arxiv.org/abs/2510.14686 https://arxiv.org/pdf/2510.14686 https://arxiv.org/html/2510.14686
If you are at #COLM2025, come by the Workshop on the Application of LLM Explainability to Reasoning and Planning TODAY at 2:40 ET to see my talk on challenges in human-agent communication and how the interpretability community can help address them!
xllm-reasoning-planning-workshop.github.io
xllm-reasoning-planning-workshop.github.io
XLLM-Reason-Plan
Website for the Workshop on the Application of LLM Explainability to Reasoning and Planning at COLM 2025
xllm-reasoning-planning-workshop.github.io
October 10, 2025 at 4:46 PM
If you are at #COLM2025, come by the Workshop on the Application of LLM Explainability to Reasoning and Planning TODAY at 2:40 ET to see my talk on challenges in human-agent communication and how the interpretability community can help address them!
xllm-reasoning-planning-workshop.github.io
xllm-reasoning-planning-workshop.github.io
📣Tomorrow at #COLM2025:
1️⃣ Purbid's 𝐩𝐨𝐬𝐭𝐞𝐫 at 𝐒𝐨𝐋𝐚𝐑 (𝟏𝟏:𝟏𝟓𝐚𝐦-𝟏:𝟎𝟎𝐩𝐦) on catching redundant preference pairs & how pruning them hurts accuracy; www.anamarasovic.com/publications...
2️⃣ My 𝐭𝐚𝐥𝐤 at 𝐗𝐋𝐋𝐌-𝐑𝐞𝐚𝐬𝐨𝐧-𝐏𝐥𝐚𝐧 (𝟏𝟐𝐩𝐦) on measuring CoT faithfulness by looking at internals, not just behaviorally
1/3
1️⃣ Purbid's 𝐩𝐨𝐬𝐭𝐞𝐫 at 𝐒𝐨𝐋𝐚𝐑 (𝟏𝟏:𝟏𝟓𝐚𝐦-𝟏:𝟎𝟎𝐩𝐦) on catching redundant preference pairs & how pruning them hurts accuracy; www.anamarasovic.com/publications...
2️⃣ My 𝐭𝐚𝐥𝐤 at 𝐗𝐋𝐋𝐌-𝐑𝐞𝐚𝐬𝐨𝐧-𝐏𝐥𝐚𝐧 (𝟏𝟐𝐩𝐦) on measuring CoT faithfulness by looking at internals, not just behaviorally
1/3
October 9, 2025 at 4:54 PM
📣Tomorrow at #COLM2025:
1️⃣ Purbid's 𝐩𝐨𝐬𝐭𝐞𝐫 at 𝐒𝐨𝐋𝐚𝐑 (𝟏𝟏:𝟏𝟓𝐚𝐦-𝟏:𝟎𝟎𝐩𝐦) on catching redundant preference pairs & how pruning them hurts accuracy; www.anamarasovic.com/publications...
2️⃣ My 𝐭𝐚𝐥𝐤 at 𝐗𝐋𝐋𝐌-𝐑𝐞𝐚𝐬𝐨𝐧-𝐏𝐥𝐚𝐧 (𝟏𝟐𝐩𝐦) on measuring CoT faithfulness by looking at internals, not just behaviorally
1/3
1️⃣ Purbid's 𝐩𝐨𝐬𝐭𝐞𝐫 at 𝐒𝐨𝐋𝐚𝐑 (𝟏𝟏:𝟏𝟓𝐚𝐦-𝟏:𝟎𝟎𝐩𝐦) on catching redundant preference pairs & how pruning them hurts accuracy; www.anamarasovic.com/publications...
2️⃣ My 𝐭𝐚𝐥𝐤 at 𝐗𝐋𝐋𝐌-𝐑𝐞𝐚𝐬𝐨𝐧-𝐏𝐥𝐚𝐧 (𝟏𝟐𝐩𝐦) on measuring CoT faithfulness by looking at internals, not just behaviorally
1/3
In the LLM explainability in reasoning and planning workshop, Friday 9am, I'll talk about scaling up model interpretability (xllm-reasoning-planning-workshop.github.io)
XLLM-Reason-Plan
Website for the Workshop on the Application of LLM Explainability to Reasoning and Planning at COLM 2025
xllm-reasoning-planning-workshop.github.io
October 7, 2025 at 1:41 PM
In the LLM explainability in reasoning and planning workshop, Friday 9am, I'll talk about scaling up model interpretability (xllm-reasoning-planning-workshop.github.io)
Om AI Lab視覺語言大模型VLM-R1接入杭州人工智能計算中心（AICC）xLLM開源大模型推理框架，推理性能跨越式提升
Om AI Lab始終致力於推動AI技術的創新與應用
www.headline01.com
September 8, 2025 at 3:42 PM
Idly surprised no brand has staked out the XLLM / Extra-Large Language Model space
September 6, 2025 at 10:47 PM
Idly surprised no brand has staked out the XLLM / Extra-Large Language Model space
We presented our work on cross-document event-keyed summarization at XLLM@ACL last month, and I talked a bit about it at @naloma.bsky.social.
Paper: aclanthology.org/2025.xllm-1....
Slides: tinyurl.com/naloma-keynote
Data + Code: github.com/wgantt/SEAMuS
Explorer: staramus.github.io
Check it out!
Paper: aclanthology.org/2025.xllm-1....
Slides: tinyurl.com/naloma-keynote
Data + Code: github.com/wgantt/SEAMuS
Explorer: staramus.github.io
Check it out!
Home
Interactive explorer for Frames Across Multiple Sources (FAMuS) and Summaries of Events Across Multiple Sentences (SEAMuS) datasets, built on MegaWika for cross-document event extraction research.
staramus.github.io
August 18, 2025 at 3:48 PM
We presented our work on cross-document event-keyed summarization at XLLM@ACL last month, and I talked a bit about it at @naloma.bsky.social.
Paper: aclanthology.org/2025.xllm-1....
Slides: tinyurl.com/naloma-keynote
Data + Code: github.com/wgantt/SEAMuS
Explorer: staramus.github.io
Check it out!
Paper: aclanthology.org/2025.xllm-1....
Slides: tinyurl.com/naloma-keynote
Data + Code: github.com/wgantt/SEAMuS
Explorer: staramus.github.io
Check it out!
Today and tomorrow: a large number of workshops and colocated conferences. We still have three papers to present. Today I'll present in the poster session in REALM, tomorrow Lynn Greschner presents in BioNLP and Sean Papay in XLLM.
July 31, 2025 at 6:33 AM
Today and tomorrow: a large number of workshops and colocated conferences. We still have three papers to present. Today I'll present in the poster session in REALM, tomorrow Lynn Greschner presents in BioNLP and Sean Papay in XLLM.
Excited to attend #ACL2025NLP in Vienna next week!
I’ll be presenting our #NAACL2025 paper, PICLe, at the first workshop on Large Language Models and Structure Modeling (XLLM) on Friday. Come by our poster if you’re into NER and ICL with pseudo-annotation.
arxiv.org/abs/2412.11923
I’ll be presenting our #NAACL2025 paper, PICLe, at the first workshop on Large Language Models and Structure Modeling (XLLM) on Friday. Come by our poster if you’re into NER and ICL with pseudo-annotation.
arxiv.org/abs/2412.11923
PICLe: Pseudo-Annotations for In-Context Learning in Low-Resource Named Entity Detection
In-context learning (ICL) enables Large Language Models (LLMs) to perform tasks using few demonstrations, facilitating task adaptation when labeled examples are hard to obtain. However, ICL is sensiti...
arxiv.org
July 26, 2025 at 3:11 PM
Excited to attend #ACL2025NLP in Vienna next week!
I’ll be presenting our #NAACL2025 paper, PICLe, at the first workshop on Large Language Models and Structure Modeling (XLLM) on Friday. Come by our poster if you’re into NER and ICL with pseudo-annotation.
arxiv.org/abs/2412.11923
I’ll be presenting our #NAACL2025 paper, PICLe, at the first workshop on Large Language Models and Structure Modeling (XLLM) on Friday. Come by our poster if you’re into NER and ICL with pseudo-annotation.
arxiv.org/abs/2412.11923
マンスリーの石XLLM全部使って真斗君一枚も出ないしSRコインに変わるのばっかりだし、トキヤはあと一枚で完凸。
真斗君は？？？？
真斗君は？？？？
July 1, 2025 at 8:32 AM
マンスリーの石XLLM全部使って真斗君一枚も出ないしSRコインに変わるのばっかりだし、トキヤはあと一枚で完凸。
真斗君は？？？？
真斗君は？？？？
I'll be giving an invited talk at The First Workshop on the Application of LLM Explainability to Reasoning and Planning at COLM'2025
xllm-reasoning-planning-workshop.github.io
Explanability? Reasoning? Planning? Language Models? Checks all the boxes for me!
xllm-reasoning-planning-workshop.github.io
Explanability? Reasoning? Planning? Language Models? Checks all the boxes for me!
XLLM-Reason-Plan
Website for the Workshop on the Application of LLM Explainability to Reasoning and Planning at COLM 2025
xllm-reasoning-planning-workshop.github.io
June 3, 2025 at 6:14 PM
I'll be giving an invited talk at The First Workshop on the Application of LLM Explainability to Reasoning and Planning at COLM'2025
xllm-reasoning-planning-workshop.github.io
Explanability? Reasoning? Planning? Language Models? Checks all the boxes for me!
xllm-reasoning-planning-workshop.github.io
Explanability? Reasoning? Planning? Language Models? Checks all the boxes for me!
www.youtube.com/watch?v=xLlm... episode 50 crazy how i came so far on my forever world
Wander Into Pale Garden Spook Minecraft Ultimate Survival #50
YouTube video by BmaDoubleOG
www.youtube.com
April 26, 2025 at 2:56 AM
www.youtube.com/watch?v=xLlm... episode 50 crazy how i came so far on my forever world
More, the third-place winning approach in the XLLM@ACL2025 Shared Task-III, which focuses on structured reasoning from only 24 labeled examples. Our approach leverages a multi-agent framework with reverse-prompt induction, retrieval-augmented [2/5 of https://arxiv.org/abs/2504.16408v1]
April 24, 2025 at 5:56 AM
More, the third-place winning approach in the XLLM@ACL2025 Shared Task-III, which focuses on structured reasoning from only 24 labeled examples. Our approach leverages a multi-agent framework with reverse-prompt induction, retrieval-augmented [2/5 of https://arxiv.org/abs/2504.16408v1]
arXiv:2504.16408v1 Announce Type: new
Abstract: The XLLM@ACL2025 Shared Task-III formulates a low-resource structural reasoning task that challenges LLMs to generate interpretable, step-by-step rationales with minimal labeled data. We present Less is [1/5 of https://arxiv.org/abs/2504.16408v1]
Abstract: The XLLM@ACL2025 Shared Task-III formulates a low-resource structural reasoning task that challenges LLMs to generate interpretable, step-by-step rationales with minimal labeled data. We present Less is [1/5 of https://arxiv.org/abs/2504.16408v1]
April 24, 2025 at 5:56 AM
arXiv:2504.16408v1 Announce Type: new
Abstract: The XLLM@ACL2025 Shared Task-III formulates a low-resource structural reasoning task that challenges LLMs to generate interpretable, step-by-step rationales with minimal labeled data. We present Less is [1/5 of https://arxiv.org/abs/2504.16408v1]
Abstract: The XLLM@ACL2025 Shared Task-III formulates a low-resource structural reasoning task that challenges LLMs to generate interpretable, step-by-step rationales with minimal labeled data. We present Less is [1/5 of https://arxiv.org/abs/2504.16408v1]
#BlueZicos 7 • multi album
the flaming lips
zaireeka •
1997
• 4 lps/cds to be played at same time
youtube.com/watch?v=XLlM...
#MusicChallenge
the flaming lips
zaireeka •
1997
• 4 lps/cds to be played at same time
youtube.com/watch?v=XLlM...
#MusicChallenge
March 8, 2025 at 5:38 AM
#BlueZicos 7 • multi album
the flaming lips
zaireeka •
1997
• 4 lps/cds to be played at same time
youtube.com/watch?v=XLlM...
#MusicChallenge
the flaming lips
zaireeka •
1997
• 4 lps/cds to be played at same time
youtube.com/watch?v=XLlM...
#MusicChallenge
im just an XLLM, extra large language model
December 2, 2024 at 6:17 AM
im just an XLLM, extra large language model
3 ways the pandemic changed your #work brain 🤔 http://rite.link/XllM
The thing I want to know is, how do we resolve the disputes around these changes?
#Business #Startup #Leadership
The thing I want to know is, how do we resolve the disputes around these changes?
#Business #Startup #Leadership
December 1, 2024 at 6:22 AM
3 ways the pandemic changed your #work brain 🤔 http://rite.link/XllM
The thing I want to know is, how do we resolve the disputes around these changes?
#Business #Startup #Leadership
The thing I want to know is, how do we resolve the disputes around these changes?
#Business #Startup #Leadership