REMORY: Learning Residual Memory for Context Compaction
Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent decision. We introduce REMORY, a ...
Papers
BrickBench: Evaluating Agentic Brick Design
We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with producing an assembly that not only satisfies semantic and ...
Predicting Cable Dynamics with Physical Attention Bias
Learned simulators for deformable linear objects (DLOs) such as cables have to predict the motion of cables they were not trained on and stay stable over long rollouts. Most of the...
BudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion
Most image generation models rely on uniform tokenization, allocating the exact same computational budget to equally-sized image patches. This static paradigm cannot adapt to diffe...
OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning
Multimodal large language models (MLLMs) are rapidly evolving toward continuous audio--visual reasoning, creating an urgent need for evaluations that expose their capability limits...
Universal Textual Teaching for LLMs
Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student parameters, thereby binding the...
Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict
When retrieved evidence contradicts an agent's prior beliefs, does it revise its answer, acknowledge uncertainty, or persist with an incorrect conclusion? Existing evaluations of a...
Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as Agent-as-Policy or Harness VLA queries a VLM for decision ma...
Opera: A Verbal Critic Framework for Long-horizon Coding Agents
Long-horizon coding agents need timely corrections, yet feedback can be ineffective or even harmful when it misjudges ongoing work or fails to address the underlying problem. Exist...
TokenRouter: Efficient Serving System for Token-Level LLM Routing
Large language model (LLM) routing distributes inference work across different models, advancing the cost-quality Pareto frontier of LLM serving. While coarse-grained routing at th...
Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals
In this paper, we argue that looped Transformers need their own residual connections to prevent performance degradation as the number of iterations grows. We observe that increasin...
Reasoning-Informed Visual Editing
Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but still face challenges in visual editing, particularly in following com...
UNITAS: A 3D-Native World Action Model for Embodied Manipulation
World action models (WAMs) aim to answer a coupled physical question: given a task instruction, what motion should the robot execute, and how will that motion change the surroundin...
VibeEdit: Image Editing with Canvas Instructions
In text-guided image editing, describing the desired change is often straightforward, but identifying the intended object or region can be cumbersome, especially when several objec...
From Prompting to Composing: A Spatial Canvas Interface for Poster Generation
Text prompting is an indirect interface for poster generation, requiring users to encode inherently two-dimensional composition intent into a one-dimensional sequence of words. We ...
SuperNav: An Agentic Navigation System for Any Task in Any Scene
General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality with scene generality. Some exis...
Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers
Dense retrievers have made significant progress on text and image corpora, but whether these capabilities extend reliably to mixed corpora containing text, image, and fused text-im...
SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference
The memory-bound nature of the decoding stage of large language model (LLM) inference incurs significant latency. Layer-wise training-free network pruning approaches guided by the ...
USDCraft: Geometrically Grounded Programmatic Modeling of Articulated 3D Assets for Simulation
Geometrically faithful and functional articulated 3D assets are essential for real-to-sim robot manipulation, where policies trained in simulation must transfer to physical objects...
AgentGarten: Code Worlds for Evolving Agents
Interactive virtual worlds allow agents to learn through exploration and interaction. What agents can learn is bounded by the environments they practice in, which must be faithful,...
V-CoLA: Vision Token Compression with Linear Attention
Vision-language models (VLMs) have demonstrated impressive capabilities but suffer from substantial computational overhead, as vision tokens dominate the input sequence. This motiv...
SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model
A 4D audio-visual scene comprises a video, the dynamic geometry it depicts, and the sound sources that populate it, each with its own position and trajectory. Rendering such a scen...
One Model to Loop Them All: Elastic Latent Recurrence for Language Models
A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing the loop count. At one loop, h...
Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective
Event sequences are chains of random events, each described by heterogeneous (numerical and categorical) features. The problem of event sequence forecasting occurs in finance, heal...