Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
DiffSAC: Diffusion-guided Sampling for Consensus-based Robust Estimation
Fine-Grained Multi Image Object Hallucination Benchmark
SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learn…
Understanding Deep Learning via Notions of Rank
BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice
Useful Memories Become Faulty When Continuously Updated by LLMs
COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models
From Extraction to Governed Memory: Multi-Agent Knowledge Graph Construction with Domain-…
How Language Models Choose Sides: Internal Representations of Instruction Hierarchy
Learning Composable Chains-of-Thought
Toward Generalizable Deep Learning Based Peatland Fire Detection via Walsh Hadamard Trans…
Gurukul AI: An Interactive AI-Driven Educational Platform for Indian Education System
Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personal…
BiG-SURE - Bipartite Graph for Semantic Uncertainty and Reliability Estimation of LLMs
Self-Evolving Skills via Surrogate-Guided Solve-and-Reproduce
A Generalized Optimization Engine (GOE) for Edge AI Inference Acceleration
Collapsibility of Performance Metrics in Clinical Predictive AI
Do Language Models Reason Across Languages?
PeopleSearchBench: Evaluating AI-Powered People Search Platforms with Criteria-Grounded V…
Retrieval-Augmented LLM Agents: Learning to Learn from Experience
Correctness Forensics for Batch Speculative Decoding: Diagnosing the Ragged Tensor Problem
A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature Sum…
Proof2Hybrid: Automatic Mathematical Benchmark Synthesis for Proof-Centric Problems
WebXSkill: Skill Learning for Autonomous Web Agents
ASTRA - Agentic System for Ticket Resolution and Analysis
MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice
An Efficient Sparse Fine-Tuning with Low Quantization Error via Neural Network Pruning
CrossAudit: A Git-Native, Cross-Vendor Audit Loop for Agentic Science