Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction
Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Lar…
AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kerne…
AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language…
Adapting Technical-Service LLM Agents with Latent Logic Augmentation, Robust Noise Reduct…
Behind Harmful Compliance: Behavioral and Mechanistic Divergence Across LLM Jailbreaks
Spatiotemporal Heterogeneity of AI-Driven Traffic Flow Patterns and Land Use Interaction:…
CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation
Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabiliz…
US-JEPA: A Joint Embedding Predictive Architecture for Ultrasound
Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets
AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots
DL$^3$M: A Vision-to-Language Framework for Expert-Level Medical Reasoning through Deep L…
Do Large Language Models Know What They Don't Know II? A Fully Behavioral, Non-Cognitive …
BETA-Labeling for Multilingual Dataset Construction in Low-Resource IR
Learning Counterfactual World Models for Embodied Reasoning under Partial Observability
AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories
Semantic Context-aware mOdality fUsion Transformer (SCOUT): A Context-Aware Multimodal Tr…
Unsound Search with Policy and Value Networks in Legends of Code and Magic
Planning and Scheduling Business Processes under Control-Flow Uncertainty
Hypersolid: Emergent Vision Representations via Short-Range Repulsion
PopResume: Causal Fairness Evaluation of LLM/VLM Resume Screeners with Population-Represe…
What Does an LLM-Agent Leaderboard Rank Actually Compare?
TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs
Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning
Who Laughs with Whom? Disentangling Influential Factors in Humor Preferences across User …
Multimodal Resource-Exhaustion Attacks on Vision-Language Models via Joint Pixel-Prompt O…
MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grou…
A radiographic world model for clinical reasoning and evidence generation