MOSS-Image Technical Report
Recent closed-source image generation systems can produce diverse visual content from simple compositions to information-dense graphics, yet open-weight text-to-image models still ...
Papers
EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?
Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteratio...
Language Models Learn to Improve Language Models
Large language models (LLMs) are increasingly used to automate AI research, including language-model (LM) development, offering a potential path toward recursive self-improvement. ...
Competence-Based Evaluation of Logical Reasoning in Large Language Models
Recent advances in large language models (LLMs) have brought impressive performance across diverse tasks; however, shortcomings remain in logical reasoning, including inconsistenci...
ABF-Bench: A Verifiable Benchmark for Agentic Blockchain Forensics
Blockchain forensics is adversarial and open-ended: money launderers split, swap, and bridge funds, cut their trail at mixers or custodial services, and change tactics from one inc...
StopWatch: Goal Grounding for Object-goal Navigation
Pretrained VLMs bring rich world knowledge and semantic priors to object-goal navigation, and fine-tuning a VLM into a navigation policy has become a common recipe. Despite this pr...
Persistent Planar Memory for Video World Models
Video world models that generate and explore environments at scale need a persistent 3D memory of what they have produced. Plane primitives offer a natural candidate: a compact set...
Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning
Reinforcement learning with verifiable rewards has become a scalable post-training paradigm for large language models. However, training agents over long-horizon interactions prese...
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
Scientific discovery requires developing worthwhile hypotheses into practical investigations, yet learning from this evolving research process remains challenging. We introduce an ...
Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generation
Generating complete, coherent, and usable 3D indoor scenes from natural language requires strong design intelligence: the ability to design high-quality scenes and critique their q...
OfficeTown: Generative Organizations for Evolving Agent Intelligence
AI agents increasingly use files and software tools to produce professional deliverables. Such work draws on materials, decisions, and feedback accumulated across assignments. We i...
QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity
Open-ended search combined with foundation models has produced advances such as faster algorithms, new results on open mathematical problems, and self-improving agents. We extend t...
Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL
Language models are increasingly trained against several verifiable rewards at once, such as the correctness and the format of a tool call, or the individual constraints of a compl...
Co-Evolving Acting and Forecasting for Language Agents
Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leav...
RSIFlow: Adaptive Self-Improvement Workflows with an Evolving Meta-Agent
Large language model (LLM) agents have demonstrated strong capabilities in complex tasks, including code generation, tool use, and multi-hop question answering. Existing self-impro...
Training Reasoning Models to Generate Diverse Scientific Ideas
One of the first steps of a research pipeline is generating ideas. Large Language Models (LLMs) are increasingly used to automate this step, but most of this work optimizes the qua...
ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning
Image editing models produce impressive results for individual edits, but their quality often deteriorates over multiple editing turns. Each editing turn introduces small distribut...
CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models
Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech to...
AlphaBet: Reinforcement Learning for LLM Event Forecasting Agents
Forecasting an unresolved event requires finding relevant evidence and deciding how strongly it supports each outcome. Yet outcome-based training of Large Language Model (LLM) fore...
Exploring The Empirical Privacy Landscape of Synthetic Data
Methods for training language models on sensitive data differ in how they balance capability gains against the risk of leaking private information. In this paper, we present a cont...
Dusting the Phantom: Gaussian Allocation for Fading Dynamic Content
Dynamic Gaussian representations have made high-quality, real-time volumetric video increasingly practical, yet challenging motion can still break their reconstruction: small fast-...
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with complex, c...
GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations
Text-based world models have recently shown potential to simulate complex RL environment state transitions for a diverse set of use cases. However, no standardized benchmark exists...
DuET: Note-Frame Dual Encoding for Piano Performance-to-Score Transcription
Transcribing expressive piano performances into scores requires interpreting individual note timings within an underlying metrical structure. However, score attributes are associat...