AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scena…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
MEMO: A Modular Framework for Training a Dedicated Memory Model on New Knowledge Without …
An Evolutionary Approach for Designing Stable and Highly Expressible Low-Immunogenicity T…
KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evalua…
Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning
Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents
Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency
GeneralThinker: Domain-General Reasoning through Likelihood-Guided Answer-Conditioned Opt…
When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
Strategic Persuasion with Trait-Conditioned Multi-Agent Systems for Iterative Legal Argum…
From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Ques…
Understanding the Challenges in Iterative Generative Optimization with LLMs
Innovation: An Almost Characterization of Hallucination
A Sharper Picture of Generalization in Transformers
SenBen: Sensitive Scene Graphs for Explainable Content Moderation
Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-…
The ATOM Report: Measuring the Open Language Model Ecosystem
LUCoS: Latent Unsupervised Context Selection for Tabular Foundation Models
Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Langua…
Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR
InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?
AI evaluation may bias perceptions: The importance of context in interpreting academic wr…
The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing …
When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning
Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery …
Intelligent Detection and Mitigation of Carpet-Bombing DDoS Attacks in SDN Using Retrieva…
BioFact-MoE: Biologically Factorized Mixture of Experts for Vision-Language Prognostic Mo…
Few-shot Cross-country Generalization of Tabular Machine Learning and Foundation Models f…