Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 22,521 papers.
3 Jul 2026
We propose PRECEDE, a precedent-guided co-scientist for side-effect-aware drug redesign that revises a parent compound to mitigate a specified side effect while preserving therapeutic function.
3 Jul 2026
Multi-product kitting delivery imposes significant challenges for real-time scheduling in hybrid manufacturing systems that integrate processing and assembly, as dynamic order arrivals simultaneously alter supply dependencies and the set of feasible job-machine assignments.
3 Jul 2026
Adversarial robustness in Unsupervised Domain Adaptation (UDA) remains a significant challenge due to noisy pseudo labels and inherent distributional shifts between the clean source and adversarially perturbed target domains.
3 Jul 2026
Least privilege, the principle that an identity should hold only the permissions strictly required for its task, has been a foundational primitive of access control for decades.
3 Jul 2026
Large Language Model (LLM) serving has become a critical cloud workload, and realistic traces are essential for motivating and benchmarking serving systems. However, existing LLM serving workload studies remain limited in scale and scope.
3 Jul 2026
Outcome-supervised reinforcement learning scales to verifiable reasoning tasks, but trajectory-level rewards assign the same outcome signal to all sampled tokens, overlooking their unequal contributions to the reasoning process.
2 Jul 2026
Safe motion planning in advanced driver-assistance systems and autonomous vehicles requires an accurate understanding of how the surrounding traffic scene is likely to evolve.
2 Jul 2026
Electroencephalography (EEG) offers a noninvasive approach for examining neurophysiological correlates of dimensional psychopathology, yet systematic evidence across EEG paradigms and feature granularities remains limited.
2 Jul 2026
Linear-attention and state-space language models compress the prefix into a fixed-size recurrent state, yielding O(1) memory at the cost of a lossy exact memory: when many key--value associations compete, earlier facts are overwritten and needle recall degrades.
2 Jul 2026
These notes give a proof-oriented introduction to diffusion models from the viewpoint of sampling, tracing a single arc from classical sampling dynamics to modern diffusion samplers, their error analysis, and inference-time control.
2 Jul 2026
Motivated by the challenge of stabilizing a general unknown linear dynamical system (LDS) from observations, we study the natural prerequisite of online prediction. Our goal is to achieve sublinear regret with a memory footprint that adapts to the intrinsic complexity of the…
2 Jul 2026
A/B testing is the gold standard for selecting the better algorithm in online services. While offline evaluation has attracted attention as a safer alternative due to the high experimental costs and the potential risk of degrading user experience and revenue in A/B testing, it…
2 Jul 2026
This technical report describes our system for Task 1 of the DCASE 2026 Challenge, which aims to classify heterogeneous audio recordings according to the Broad Sound Taxonomy (BST).
2 Jul 2026
Predictions by machine learning (ML) and artificial intelligence (AI) models are often received skeptically unless they are paired with intelligible explanations. In the context of just-in-time defect prediction, highlighting small portions of a software change (diff) -- beyond…
2 Jul 2026
Multiple-choice medical benchmarks are increasingly saturated, and recent rubric-based evaluations such as HealthBench have shown that open-ended clinical performance is far from solved - its "Hard" subset top score remains 32%.
2 Jul 2026
Long term memory lets LLM agents act as persistent assistants, but user facts change. A useful memory system must know what is true now, what used to be true, and what changed.
2 Jul 2026
Most LP-from-text benchmarks are static datasets of word problems written and labeled by hand. Once such a dataset is released, its size is fixed, its difficulty is fixed, and every problem can leak into the training data of future LLMs.
2 Jul 2026
Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control. However, the standard planning cost judges a candidate solely by how close its predicted terminal state lies to the goal, leaving the realizability of the intermediate…
1 Jul 2026
The game of Taboo requires describing a target word without using a set of forbidden words, so that other players can guess it. This deceptively simple task combines strict lexical constraints with the need for communicatively effective descriptions, making it a compelling…
1 Jul 2026
Quantization has become an invaluable tool to reduce memory requirements and inference speed of modern language models, in particular to make them available for consumer setups and edge devices.
1 Jul 2026
Continuous diffusion language models offer an alternative to autoregressive generation, but their generations may suffer from repetition. We find that unconditional generations from ELF, a recent family of continuous diffusion language models, are more repetitive than human…
1 Jul 2026
Industry pipelines that turn speech into supervised fine-tuning (SFT) data via multi-stage refinement are increasingly adopted but, to our knowledge, have not been publicly ablated stage-by-stage, leaving each stage's marginal value unknown.
1 Jul 2026
While prior work has explored emotion control in hybrid text-to-speech systems, the geometric properties of these modules, and their implications for steerability, remain poorly understood.
1 Jul 2026
Deep multimodal brain-encoding models now predict fMRI responses to naturalistic video with high accuracy; whether their predicted neural signals also forecast behavioral engagement is unknown.