TraceCodec: A Compiler-Backed Neural Codec for Stateful Multi-Flow Network Traffic Traces
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Harnessing non-adversarial robustness in large language models
Energy-Aware NECO for Single-Pass Pixel-wise Out-of-Distribution Detection in Semantic Se…
From XXLTraffic to EvoXXLTraffic: Scaling Traffic Forecasting to Sensor-Evolving Networks
EMAG: Differentiable 4D Gaussian Mixture Splatting for EEG Spatial Super-Resolution
Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
User-Aware Active Knowledge Acquisition for Emotional Support Dialogue
BitTP: The Lightweight Trajectory Prediction Model with BitLLM for Edge-Devices
A Systematic Evaluation of Molecular Mixture Behavior Prediction
Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM …
Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision …
Predicting Causal Effects from Natural Language Queries using Structured Representations
Entity-Collision: A Stratified Protocol for Attributing Retrieval Lift in Agent Memory
CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Ref…
DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Super…
From General Vision to Reliable Traversability Estimation: Adapting Vision Foundation Mod…
ESAM++: Efficient Online 3D Perception on the Edge
AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained…
A Eureka machine that thinks like nature and explores what AI cannot
How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignmen…
When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role…
Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A…
TRACER: Persistent Regularization for Robust Multimodal Finetuning
WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study
The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces
DiagramRAG: A Lightweight Framework to Retrieve Scientific Diagram for Figure Generation
Dr-CiK: A Testbed for Foresight-Driven Agents
Towards Faithful Agentic XAI: A Verification Method and an Open-World Benchmark for Bette…