CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language M…
Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence
Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents
Post-Training Language Models for Gold-Medal Performance in Coding Competitions
Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts
Knowing Is Not Enough: Information Retrievability as a Precondition to Effective LLM Over…
CliffRank: A Dual-Branch Framework for Activity-Cliff Ranking Prediction
Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A C…
CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning
RecKAN: Kolmogorov-Arnold Networks with a Learnable Recursive Polynomial Basis
Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain …
Reinforcement Learning for Heterogeneous Sensor Selection in Maritime Surveillance
Ranked by the Matcher: A Reproducibility Audit of Knowledge Graph Extraction from Threat …
hLLM: Single Pass Decoding for Generative Reranking
A Data-Driven Multimodal Method for Early Detection of Coordinated Abnormal Behaviors in …
From Feature Interaction to Feature Transport - A Unified Block for Scalable Recommendati…
Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance
PolERo: Studying Political Evasion in Romanian
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fi…
Two Centuries of Sexism in British Parliament: A Computational Analysis of Women's Repres…
PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation
How Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for …
Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxon…
EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation…
GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories
WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling
Hybrid Retrieval-Augmented Generation with Knowledge Graph Expansion, RRF Fusion, and Per…
RecEvolve: A Knowledge-Driven Autonomous Agent System for Recommender Systems
Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems