Prompt-specialized multi-agent systems enable multiple agents to share a model while performing complementary roles to solve complex tasks. However, agent-specific prefixes change ...
On-policy distillation (OPD) is a widely adopted post-training technique for LLM reasoning. It is commonly believed to transfer knowledge from a stronger teacher, yet what OPD actu...
Multi-LoRA agent systems enable efficient role specialization by sharing a common backbone model. However, each agent repeatedly processes the growing shared trajectory and constru...
Machine intelligence is often evaluated through abstract reasoning problems, yet many real-world problems are visual, such as arranging objects, repairing layouts, or tracing route...
In multi-agent systems, reliable consultation is challenging because advisor capabilities vary across tasks, and misleading information can make consultation worse than autonomous ...
We present EditWorld, a video world model for precise editing and flexible referencing in interactable worlds. Existing video world models primarily focus on navigation, letting us...
Guard models support the safe deployment of language model agents, but fixed risk taxonomies limit their ability to accommodate requirements that vary across applications and tasks...
Reinforcement learning (RL) has become a key paradigm for enhancing the reasoning of large language models, yet the high dimensionality of parameter updates makes its training dyna...
Vision-language (VL) pretraining using paired chest X-ray (CXR) images and radiology reports has shown strong potential for medical image understanding. However, existing methods o...
Names are personal identifiers, but they also carry social meaning and are widely used to evaluate how language models treat different people. Such evaluations typically assume tha...
Large language models (LLMs) excel at structured, verifiable tasks, but their low-entropy bias can produce homogeneous and predictable outputs, limiting their utility for open-ende...
Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged template marker such as can reach the ...
Humans naturally possess the ability to work persistently toward long-term goals. Given a challenging task, humans can continuously work for months or even years to accomplish a sp...
In ecology, psychometrics, and the analysis of social and financial networks, binary matrices are often analyzed conditional on their observed row and column sums, which restricts ...
Video and audio are perceived together, yet most generative models treat them in isolation. We examine methods that model the two modalities jointly, generate one from the other, o...
Large language models can reason in continuous space instead of decoded text, by recurring on their own hidden states or by passing those states between agents, while training supe...
Open-vocabulary semantic segmentation (OVSS) enables pixel-level prediction over arbitrary text-specified vocabularies and has shown strong generalization on common benchmarks. How...
Robots that learn from a few demonstrations often require two forms of generalization. Compositional generalization recombines skills to solve new tasks, and skill generalization l...
We present LongCat-DeepResearch, a deep research system that combines an enhanced LongCat model with a multi-agent workflow for producing comprehensive, evidence-grounded reports. ...
As large language models are deployed in increasingly autonomous long-horizon tasks, manually auditing and verifying the actions, artifacts, and outputs of models becomes more diff...
Video-language models are increasingly used as judges of video understanding, both for evaluating model outputs and for training reward models. Whether their judgments remain relia...
Multi-teacher on-policy distillation (MOPD) has emerged as a popular post-training paradigm for integrating specialized capabilities in frontier language models. Existing OPD resea...
Artificial-intelligence (AI) agents hold promise for automating bioimage analysis, yet no benchmark evaluates whether they can carry out real-world analyses end to end. Such analys...
Realistic and editable animal fur reconstruction from multi-view images is challenging due to fine-scale detail, self-occlusion and obfuscation, and, unlike human hair, the lack of...