Image Tokenizers Should Be Trained Between Images
Latent diffusion models generate images as codes of an image tokenizer, whose decoder turns them into the pixel image. Recent tokenizers improve how well these codes reconstruct an...
Papers
RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models
Video-based interactive world models aim to enable real-time, user-controllable environments. Yet most existing systems are trained and rolled out at a fixed temporal rate, limitin...
Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues
LLM-based multi-agent collaboration is increasingly used to solve complex tasks by dividing work among specialized agents and integrating complementary expertise. Yet existing syst...
Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations
Existing interpretability tools do not test whether a representation keeps the same content when only the phrasing changes. We treat each paraphrase pair as a local witness that tw...
EventLens: Event-Structure Reinforcement Learning for Video Understanding
Recent multimodal large language models (MLLMs) achieve strong results on video question answering, yet often fail to recover the temporal structure that makes a video coherent. Th...
ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty
Evaluating model uncertainty on real-world data is challenging because each instance provides only a single observed label, leaving true conditional class probabilities unknown. To...
Multics: Generative Multi-Player World Model with Hierarchical Communication
Multi-player interactive world models aim to simulate shared environments from multiple players' perspectives, but achieving robust generation while scaling to more players remains...
VEDJE: Video-Efficient Discriminative Joint Encoder for Scalable Video-Text Retrieval
Finding the right video often requires distinguishing similar scenes in which different events occur. Joint matching improves retrieval, but processing rich video representations f...
Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR
Reinforcement learning with verifiable rewards (RLVR) typically uses small rollout groups per prompt, where repeated sampling from the same policy can yield highly similar trajecto...
FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation
Linear-time sequence models typically store long-context information in a recurrent state. A fixed-size state limits how much information can be stored, while hybrid architectures ...
DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck
Evaluation has been central to advances in AI, and it is equally critical to autonomous discovery. Yet scaling autonomous discovery to real-world engineering challenges faces a fun...
Self-Distillation with Verbal Regularization
On-policy self-distillation (OPSD) trains a large language model using supervision from a teacher instantiated from the same model as the student. The teacher is conditioned on pri...
TPPO: Tracking-Value PPO For Language Model Reasoning
Proximal Policy Optimization (PPO) is widely used in reinforcement learning with verifiable rewards for language-model reasoning. While value evolution along trajectory characteriz...
Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards
Reinforcement learning with verifiable rewards (RLVR) is reshaping how large language models (LLMs) acquire reasoning capabilities, yet the optimizers used remain largely inherited...
Heterogeneous Agentic Coevolution
Recent advances in self-improving LLM agents have demonstrated the potential of AI systems that drive their own intelligence. However, many domain-specific applications rely on spe...
InfoVis: Unified Slide Image Generation and Editing
Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design, and precise editing within...
MixLID: Token-Level Language Identification in Mixed-Language Text
Processing multilingual text requires both identifying a broad range of languages and distinguishing the language of each token in inputs containing multiple languages. We introduc...
AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding
Vision-language-action (VLA) models show strong potential for end-to-end autonomous driving by leveraging world knowledge and understanding to excel in long-tail scenarios. However...
EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents
Training LLM agents to interact with users over multiple turns is challenging because the learning signal depends not only on the agent, but also on the user simulator and environm...
Rethinking LLM-Guided Visual Question Answering: Does Deeper Knowledge Integration Really Help?
Knowledge-based Visual Question Answering (VQA) requires reasoning that extends beyond visible image content, demanding external commonsense and factual knowledge. While recent wor...
LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators
Generative discovery in science requires coupling high-level scientific reasoning with the ability to generate samples respecting the structure of a design space. Yet these capabil...
EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications
Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily evaluate development toward f...
When Left Is Right? Camera-Motion Understanding beyond Screen
Can a vision-language model tell left from right? Modern VLMs solve visual puzzles and follow hour-long videos, yet when asked whether the camera moved left or right, most do no be...
LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards
Reinforcement Learning (RL) has emerged as a key driver for LLM reasoning. This capability is equally pivotal in long-context scenarios---such as long-dialogue understanding and st...