Cross-Primitive Consistency in Jev
Jev enables efficient decision-making with large language models (LLMs) through typed querying primitives, allowing the same semantic state to be expressed in different formats, su...
Papers
Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
Financial agents must form forecasts and investment judgments from decision-time evidence, with predictions evaluated against subsequent outcomes. Existing benchmarks assess financ...
A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
Recursive self-improvement requires models not only to acquire useful training experience, but also to decide when their current experience has ceased to be useful. Existing method...
AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding
Recent advances in multimodal large language models have increased interest in interaction paradigms for video understanding. The evolution from offline to streaming and proactive ...
A Tutorial on Generative Models for Music Audio
Music audio generation spans instrumental clips, full songs with vocals, edits of existing recordings, and systems that play alongside a musician in real time. This monograph expla...
Multi-Token Prediction Done Right
Multi-Token Prediction (MTP) is now a common ingredient in language-model pre-training, as it improves downstream performance and enables faster inference through speculative decod...
SciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World
Large language model agents are increasingly used for scientific discovery. However, existing benchmarks mix law inference with programming, score data fitting instead of predictio...
LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation
We present LCM-Promo, an LLM-based uplift model for promotion allocation. LCM-Promo is a task-specific Large Commerce Model (LCM): a finetuned LLM trained on transactional commerce...
AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending Operations
Large language model (LLM) agents are extending agent-mediated commerce on the Web from shopping for consumers to operating businesses for sellers. In online-to-offline (O2O) comme...
Muon Makes the First Mixture-of-Experts Layer Harder to Balance
Many open mixture-of-experts (MoE) language models train with Muon instead of AdamW. Most balance the load with a bias on each expert's routing score, adjusted after every step. Th...
Vision-Language-Action or World-Action? Just Action Models
The vision-language-action (VLA) and world-action model (WAM) communities debate whether control policies should inherit pretrained knowledge from vision-language models or from vi...
Timestral
We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art...
Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data
Mixture-of-Experts (MoE) models are bottlenecked by loading routed-expert weights from memory during interactive decoding at small batch sizes. Because most intermediate channels i...
CodeCap-Bench: Can Code Serve as a Good Video Caption?
Video captioning aims to preserve visual information through compact descriptions, predominantly using natural language. However, precisely expressing fine-grained spatial structur...
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of action-lab...
WebAnything: From the Wild Web to Scalable Agent Environments
Web agents require diverse, executable, and resettable website environments for reproducible training and evaluation. Human-assisted mirrors demand per-site engineering, while gene...
Do We Need an LLM to Know Why Sources Conflict? Decision Models for Knowledge-Conflict Typing in RAG
When the sources retrieved for a query disagree, the right response depends on why they disagree: a question with several valid answers, a contested topic, stale information and a ...
PREEN: Exemplar-Based Color Style Transfer with Smartphone Editor Presets
We present PREEN (Preset Regression via an Exemplar-based Editor Network), which casts color style transfer as regression onto the 29 parameters of a deterministic image editor. Gi...
WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training
Scaling supervised training for working agents requires diverse professional tasks that yield reliable expert demonstrations. However, missing or inconsistent task information can ...
Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception
Multimodal perception forms the foundation of multimodal intelligence. In particular, spatial perception and multimodal long-context understanding are two pivotal tasks that underp...
Know, then Draw: A New Learning Paradigm for Visual Generation
Visual generation requires both high-level semantic knowledge and fine-grained pixel details. We propose a learning paradigm that assigns these roles to autoregressive pretraining ...
Quaternion Approximate Networks for Enhanced Image Classification and Oriented Object Detection
This paper introduces Quaternion Approximate Networks (QUAN), a novel deep learning framework that leverages quaternion algebra for rotation equivariant image classification and ob...
Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling
Robot policy evaluation often relies on a binary success signal for task completion. In real-world deployment, however, desired execution behaviors are also defined by quality attr...
Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions
When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claim...