Pass the Baton: Trajectory-Relayed On-Policy Distillation
On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix failure: once the student commits to a wrong reasoning direction, all…
Latest
Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking
Multimodal automated fact-checking (MAFC) verifies claims by retrieving and reasoning over external evidence. However, most existing static benchmarks risk contamination: they primarily consist of outdated claims…
Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion
We present a reproducible pipeline for mapping Common Vulnerabilities and Exposures (CVEs) to MITRE ATT&CK Enterprise techniques from free-text vulnerability descriptions. Rather than relying on the…
ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition
Recovering an editable design file from a raster image is a common and costly bottleneck in modern design workflows, yet remains challenging since editability depends on…
Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception tasks and process them inefficiently.…
A New Role for Relevance: Guiding Corpus Interaction in Agentic Search
Relevance is a query-dependent estimate of whether a document or excerpt contains useful evidence. Existing retrieval agents use relevance to select top-k content, but document relevance…
HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone
Learning deployable manipulation policies is bottlenecked by the scarcity of data that is both high-fidelity and scalable. Real-robot teleoperation is accurate but costly to scale; robot-free…
PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models
We introduce PerceptionBench, a benchmark specifically designed to evaluate the atomic visual perception capabilities of Multimodal Large Language Models (MLLMs). Existing benchmarks often fail to isolate…
Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory
Long-term memory systems store what a user says in an external store and retrieve it when a related query arrives. This interface rests on an assumption…
Visual prompt engineering for video models
In the age of foundation models, a model is only as good as its prompt. For this reason, prompt engineering has become an essential technique for…