Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain ov…

Reinforcement Learning with Verifiable Rewards (RLVR) has been central to the recent success of Large Reasoning Models. …

Chain-of-Thought (CoT) improves the reasoning ability of Large Language Models (LLMs) but incurs substantial computation…

Large language models (LLMs) are often post-trained on pre-collected reasoning trajectories to improve their reasoning c…

Latent visual reasoning aims to perform multimodal reasoning through hidden-state computation rather than explicit textu…

Reasoning in large language models unfolds through diverse functional operations, such as problem formulation, goal deco…

Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but t…

A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers prov…

Despite the remarkable prowess of Vision-Language Models (VLMs) in general multimodal tasks, they remain fundamentally `…

Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on…

Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, sideste…

Invasive coronary angiography (CAG) is the gold standard for diagnosing coronary artery disease, but interpretation vari…

Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral signals, yet existing b…

Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of …

Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally bli…

Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the pro…

Large Language Models demonstrate remarkable proficiency in static reasoning, yet training them as autonomous agents thr…

Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from …

Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose …

On-Policy Self-Distillation (OPSD) has emerged as a popular paradigm for large language model (LLM) self-improvement, al…

把 2026 年可核查的公开证据整理成一张六层能力路线图——预训练、后训练 RL、推理时计算、上下文与记忆、智能体与 Harness、世界模型。含 Meta ScaleRL 40 万 GPU 小时实验结论、RL 预算占比 10%–30% 口径、Chinchilla 对比、Meta-Harness 6x 差距等数据锚点，并给出优先级表与算法工程师/产品经理的行动建议。

Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and …

Sequential memory agents process long documents by reading chunks one after another while maintaining a compact memory s…

Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation. However,…

Reinforcement learning with verifiable rewards (RLVR) substantially improves single-sample accuracy (pass@1) but causes …

Instance segmentation of overlapping cells in microscopy remains challenging due to semi-transparent structures that pro…

Audio-visual understanding remains challenging because models must jointly interpret spoken content, visual events, and …