The SIMPLE Law for Energy Cost of LLM Inference
Generative AI is billed per token, yet tokens are not equally expensive. Each token enters the KV-cache and raises the cost of those that follow, so energy grows non-linearly along...
Papers
PhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing with Explainable Photographic Assessments
Traditional image cropping assumes the photograph already contains the composition worth keeping, and asks only where to crop. A full 360^{circ} scene offers no such guarantee: the...
Every Pixel Is an Option: A System One Model for Medical Ultrasound Biometry
**Purpose:** Ultrasound biometry is widely used across various clinical applications, including prenatal and cardiac examinations, to obtain quantitative measurements by placing ca...
Enhancing Stock Market Information Retrieval with Retrieval-Augmented Generation
Natural Language Processing (NLP) has been widely applied in financial domains, enabling automated analysis and retrieval of stock market information. However, traditional NLP-base...
Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attention
Sparse attention cuts the cost of long-context inference by making the attention matrix sparse: each query attends only a subset of the sequence, chosen by a fixed pattern or, in r...
SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding
Speculative decoding (SD) accelerates large language model inference by reducing the sequential cost of token-by-token generation. Advanced SD methods reduce proposal cost with par...
DR Pixel: Page-Native Deep Research with Vision-Language Models
Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to OCR-e...
WebHarbor: Docking Real Websites for Evolving GUI Agent Environments
GUI web agents require realistic and interactive environments that remain stable during both evaluation and training. Live website evaluation suffers from changing content, access ...
TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens
LLM-based agentic systems are increasingly combined with CoT reasoning to solve tasks that require accurate reasoning, external knowledge, and multi-step deliberation. Yet, explici...
When Does Latent Prediction Error Support Physical Surprise Claims in Video World Models?
Prediction errors from video world models are often treated as physical surprise, but they can also reflect appearance, static content, motion, or ordinary prediction difficulty. W...
ODE Policy: Robot Learning via Action Dynamics, Not Actions
Most robot policies, whether trained by imitation learning (IL) or reinforcement learning (RL), map observations to action values at discrete control steps and leave the continuity...
CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agents
As coding agents achieve increasingly high success rates on software engineering benchmarks, recent efforts have sought to increase task complexity through longer horizons and more...
"PRISM" Is Not All You Need: Cross-Topic Name Collisions and Scientific Paper Retrieval
Scientific names increasingly connect papers from different research topics, leaving readers to recover a paper's identity from context. We study this convergence in 564,861 AI-rel...
Democratizing Robot-Use Agents: A Unified Harness with Open Models
Robot-use Agents (RUAs) have shown promising zero-shot manipulation capabilities, but reliance on frontier, proprietary models limits research into further training. To democratize...
NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale
Scaling computer-use agents from individual actions to complex software work requires experience that connects decisions to complete outcomes. We present NorthCUA, an integrated sy...
Advances in Agentic Computer Graphics
Computer graphics is built on code. Large language model (LLM) agents can now generate graphics code and iteratively refine it through various feedback. This capability opens the d...
Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?
Software development sessions often involve several unfinished tasks rather than one issue carried through to completion. As coding agents take on repository-level development, the...
FinForesight: A Diagnostic Backtesting Benchmark for Deep Research Systems in Financial Forecasting
Anticipating financial outcomes requires synthesizing evolving evidence and reasoning under uncertainty, making deep research systems promising tools for forecasting. Yet evaluatin...
Is Your Long-Horizon Benchmark Really Deep? Measuring and Synthesizing Depth in Terminal Tasks
Long-horizon terminal tasks are used to evaluate and train agents. Human-curated datasets are scarce, so many synthesis methods have emerged. They usually measure the length of a t...
ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost
Harness optimization can substantially improve LLM agents without modifying model weights, but existing methods primarily optimize response quality. Extending them to joint quality...
QFabric: Guarded Cross-Domain Task Recovery and Its Limits on a Linux-RTOS Board
Heterogeneous embedded boards pair a Linux application processor with a real-time microcontroller (MCU), which suggests moving a task between the two domains when its timing degrad...
SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training
Coding agents solve repository issues through long sequences of exploration, editing, and validation. These trajectories are increasingly used as post-training data, so how they ar...
Can Large Language Model Agents Learn by Watching Tutorial Videos?
Humans continuously acquire knowledge from carefully crafted materials such as books and tutorial videos, carrying that understanding into future tasks. Millions of such instructio...
Can AI Reviewers See Your Efforts to Improve Your Paper? A Large-Scale Study of Paper Revision Trajectories
AI reviewers are increasingly used to assess scientific manuscripts, yet it remains unclear whether their judgments reflect the improvements authors make through revision. We inves...