ニュース
From Interpretability to Performance: Optimizing Retrieval Heads for Long-Context Language Models
arXiv:2601.11020v1 Announce Type: new Abstract: Advances in mechanistic interpretability have identified special attention heads, known...
From integration chaos to digital clarity: Nutrien Ag Solutions’ post-acquisition reset
Thank you for joining us on the “Enterprise AI hub.” In this episode of the...
From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationship
arXiv:2506.23101v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown impressive capabilities across...
From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs
arXiv:2601.03682v1 Announce Type: new Abstract: Recent studies reveal that large language models (LLMs) exhibit limited...
From hallucinations to hardware: Lessons from a real-world computer vision project gone sideways
What we tried, what didn’t work and how a combination of approaches eventually helped us...
From Gemma 3 270M to FunctionGemma, How Google AI Built a Compact Function Calling Specialist for Edge Workloads
Google has released FunctionGemma, a specialized version of the Gemma 3 270M model that is...
From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection
arXiv:2512.16439v1 Announce Type: cross Abstract: Benefiting from the superior capabilities of large language models in...
From disruption to reinvention: How knowledge workers can thrive after AI
We are beginning a cognitive migration: Away from what AI now does well, and toward...
From Correction to Mastery: Reinforced Distillation of Large Language Model Agents
arXiv:2509.14257v2 Announce Type: replace Abstract: Large Language Model agents excel at solving complex tasks through...
From Clicking to Reasoning: WebChoreArena Benchmark Challenges Agents with Memory-Heavy and Multi-Page Tasks
Web automation agents have become a growing focus in artificial intelligence, particularly due to their...
FRIDA to the Rescue! Analyzing Synthetic Data Effectiveness in Object-Based Common Sense Reasoning for Disaster Response
arXiv:2502.18452v3 Announce Type: replace Abstract: During Human Robot Interactions in disaster relief scenarios, Large Language...
Fragile Reasoning: A Mechanistic Analysis of LLM Sensitivity to Meaning-Preserving Perturbations
arXiv:2604.01639v1 Announce Type: new Abstract: Large language models demonstrate strong performance on mathematical reasoning benchmarks...
