Latest AI/ML research from ArXiv and Papers with Code
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...
Anticipating financial outcomes requires synthesizing evolving evidence and reasoning under uncertainty, making deep research systems promising tools for forecasting. Yet evaluatin...
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...
Harness optimization can substantially improve LLM agents without modifying model weights, but existing methods primarily optimize response quality. Extending them to joint quality...
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...
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...
Humans continuously acquire knowledge from carefully crafted materials such as books and tutorial videos, carrying that understanding into future tasks. Millions of such instructio...
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...
Agent decisions depend on empirical relationships that deployment observations reveal and task descriptions alone may leave unresolved. We introduce Decoupled Predictive Decision M...
On-policy distillation (OPD) trains a student on its own generations by matching the teacher's token probabilities. These probabilities entangle two kinds of information: which tok...
Streaming video LLMs can now commentate live gameplay, but they are trained and tested on the same games. We study cross-game streaming commentary, in which a model trained on one ...
Real-time long-video generation requires continuous output with consistent appearance and natural motion. Existing chunk-wise autoregressive methods face challenges in both generat...
Benchmark compression reduces the often prohibitive time and cost of model evaluation by evaluating models on a small benchmark subset that closely matches full-benchmark results. ...
Recent advances in interactive world models have made it possible to generate controllable, dynamic environments from action inputs. Yet current models struggle to maintain coheren...
Relative-position attention mechanisms offer compelling alternatives to RoPE across various transformer architectures, delivering superior performance in domains such as audio. The...
Psychotherapy clients may experience distress before they can coherently describe it, and their expression changes with emotion, perceived safety, and trust. Large language model-b...
Learning the continuous-time evolution of nonlinear dynamical systems relies on trajectory-based objectives, which require simulating the learned dynamics during training and backp...
Decision models such as Jev have emerged as a highly promising paradigm for LLM agent systems, providing lightweight and reliable categorical reasoning for rapid System One executi...
Dense 3D tracking from monocular video requires establishing point correspondences over time, estimating their depth, and inferring their trajectories during occlusion. Existing me...
Foundation models are becoming remarkably reliable at high-level reasoning, yet they remain too slow and costly to serve as fine-grained controllers. Conversely, fast policies like...
Multi-head attention in Vision Transformers (ViTs) allows independent attention patterns across heads, but without explicit regularization, heads may learn redundant patterns rathe...
Residual connections underpin Transformers, but they implicitly tie the residual width carried through depth to the compute width used inside each layer. We introduce Hierarchical ...
Computer-use agents increasingly tackle tasks ranging from everyday desktop activities to long-horizon professional workflows. Yet interfaces centered on screenshots and mouse-and-...
Existing sketch generation methods often rely on image guidance and are largely limited to individual objects or simplified scenes, leaving text-guided complex scene sketching unde...