…AI-generated summary Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful dialogue. We identify KV-cache…
…We introduce *Curation-Bench*, an agent-centric benchmark that fixes the model, training recipe, and evaluation suite while giving agents command-line access to inspect data, implement policies, submit them to a…
…AI-generated summary While video foundation models excel at single-shot generation, real-world cinematic storytelling inherently relies on complex multi-shot sequencing. Further progress is constrained by the absence of datasets…
…Benchmarking and Exploring Multi-Entity Reasoning Grounding in Remote Sensing (2026) Locatability-Guided Adaptive Reasoning for Image Geo-Localization with Vision-Language Models (2026) TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation…
…Benchmark for Structured Generation and Editing (2026) Large Language Models are Universal Reasoners for Visual Generation (2026) CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative…
…AI-generated summary Multimodal large laboratory models (MLLMs) still struggle with spatial understanding under the dominant perspective-image paradigm, which inherits the narrow field of view of human-like perception. For navigation…
…superior benchmark results and efficiency. AI-generated summary Model merging combines task experts into one model and avoids joint training, retraining, or deploying many expert models, but the merged model often still…
…AI-generated summary Distributed blackbox consensus optimization is a fundamental problem in multi-agent systems, where agents must improve a global objective using only local objective queries and limited neighbor communication. Existing…
…Benchmarking and Acoustic-Lexical Decoupled Policy Optimization (2026) Decoupling Conversational Dynamics in Full-Duplex Spoken Models through Reinforcement Learning (2026) Preference-Driven Online Adaptation for Personalized Interaction Initiation in Proactive AI Assistants…
…Adaptive Reasoning Effort Selection for Efficient LLM Agents (2026) Adaptive Vision-Language Model Routing for Computer Use Agents (2026) Anticipatory Planning for Multimodal AI Agents (2026) AgentHazard: A Benchmark for Evaluating Harmful…