ROWBench: Do Video Models Render What the Program Specifies?
Programmable world models separate executable dynamics from visual generation, offering a promising foundation for next-generation game engines. However, their visual adherence to ...
Papers
Hierarchical Continuous Diffusion Language Models
Discrete diffusion language models offer a compelling alternative to autoregressive generation for tasks demanding bidirectional reasoning and global constraint satisfaction. Yet t...
Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models
Keyword-matching benchmarks can credit small models for tool use they never perform. We document such a false positive in a matched-architecture pair of Spanish security language m...
It Takes Workflows to Evolve Better Workflows
Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that coordinate specialized agents...
AutoGUIWorld: Image Generators as Visual World Models for GUI Agent
GUI agents require high-quality interaction trajectories to learn how software environments respond to actions, maintain state, and support multi-step workflows. However, the diver...
Local Support Learning
We explore catastrophic forgetting in the context of large pre-trained models. By considering forgetting as a geometric problem in the input space of each weight matrix, we uncover...
HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution
As robotic hardware and learning methods advance, humanoids need tools to perform tasks beyond their inherent physical limits. Successful tool use requires selecting a suitable too...
SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation
Existing Simulink benchmarks mainly evaluate whether generated models compile, execute, or resemble a reference model. These criteria do not establish whether a model satisfies its...
Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
Video Large Language Models (VideoLLMs) receive frames in sequential order and interpret how visual content evolves along the temporal axis, yet temporal reasoning remains a persis...
LOCI: Spatial Linear Memory for Streaming World Models
When a camera revisits a previously observed region, a video world model should reproduce what was there before. This requires both remembering past observations and retrieving the...
Who Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across Meetings
Speech transcripts used as long-term memory must preserve both words and stable speaker identities. Existing meeting-transcription metrics either ignore speakers or remap anonymous...
EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos
Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolving object and task states. Too...
Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation
On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher that sees a reference solution and supervises student-sampled prefixes. Standard ...
Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior
Pre-pretraining (PPT) on synthetic non-natural language data improves token efficiency during language model pre-training (PT). Prior work attributes this gain to a grammatical pri...
Can Computation from Earlier Problems Help LLMs Solve New Ones?
Large language models often solve independent problems in the same conversation. Can computation from earlier problems help them solve new ones? To answer this question, we first c...
QuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code
Large language models are strong general-purpose code generators, but executable algorithmic trading remains a demanding specialization target: a model must translate a natural-lan...
Memorizon: Training World Models Beyond Their Context Window
Streaming world models should render a place consistently across repeated visits. Directly supervising such revisits requires training samples that capture both visits, often spann...
OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software
Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting specialized int...
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Self-evolving search agents build their own training curricula by jointly optimizing a proposer that generates questions and a solver that answers them. This closed loop introduces...
Benchmarking and Enhancing Skill-Level Memory for Partially Observable Robotic Manipulation
Recent advances in robot learning have enabled manipulation policies to perform increasingly diverse tasks and generalize across environments. However, reliable execution often dep...
Smaller Models, Better Rejects: Preference Distillation Scaling
Preference distillation typically treats a teacher response as preferred and the student's own response as rejected. This assumes that self-generated failures are the most informat...
Learning Functional Subspaces for Neural Network Compression
Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keeping the matrices dense, and thus ...
SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations
Given a target dataset, such as faces with eyeglasses, and a background dataset, such as faces without, contrastive analysis separates salient factors specific to the target from c...
Soft Spatial Reasoning
Large Vision-Language Models (LVLMs) commonly perform spatial reasoning through chain-of-thought (CoT), encoding intermediate reasoning as autoregressive sequences of discrete lang...