Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 14963v1 Announce Type: cross Abstract: Pareto Conditioned Networks learn multiple multi-objective reinforcement learning behaviours by conditioning a single policy on a desired return command.
arXiv:2608. 14570v1 Announce Type: new Abstract: Understanding human mobility is critical for a wide range of urban applications, including traffic management, epidemic control, and urban planning.
arXiv:2608. 14626v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved substantial progress in safety alignment, yet their safety guarantees remain significantly weaker in low-resource and multilingual settings than in high-resource languages.
arXiv:2608. 14584v1 Announce Type: cross Abstract: In Multimodal Question Answering (MQA), models are required to jointly encode and integrate heterogeneous information from multiple modalities, including text, images, and speech, to perform complex semantic reasoning and decision making.
arXiv:2608. 14619v1 Announce Type: new Abstract: This work proposes a new interpretable neural operator framework, termed the Physics Informed Kernel Function Neural Operator (PIKFNO), which explicitly incorporates physics informed kernel functions derived from governing equations into the neural operator architecture.
arXiv:2608. 15436v1 Announce Type: new Abstract: Frontier AI models have advanced rapidly, but they still struggle with telecom-specific tasks.
arXiv:2509. 21514v4 Announce Type: replace Abstract: Research on Knowledge Tracing (KT) models traditionally focuses on improving predictive accuracy.
arXiv:2605. 26182v2 Announce Type: replace Abstract: Generating physically buildable brick structures from 3D shapes requires more than geometric reconstruction: the output must also satisfy discrete part constraints and structural stability.
arXiv:2608. 15488v1 Announce Type: new Abstract: Effective public event forecasting is essential for intelligent service systems, enabling proactive risk management, adaptive resource allocation, and timely decision-making.
arXiv:2608. 14924v1 Announce Type: cross Abstract: Spatial transcriptomics (ST) links tissue morphology with molecular programs, motivating multimodal pretraining methods that align histology images with gene expression.
The paper introduces RUPA, a trajectory‑level uncertainty quantification framework for large language model agents. RUPA models an agent’s execution as a directed graph of reasoning states, tool interactions, and environment feedback, then propagates uncertainty across this graph to capture long‑range dependencies. Experiments on benchmarks such as τ‑2, Terminal‑Bench‑2, and GAIA show that RUPA outperforms existing methods, enabling earlier failure detection and more reliable agent execution.
arXiv:2608. 16804v1 Announce Type: new Abstract: Sign language serves as a vital means of communication for individuals with hearing impairments, yet recognition resources for the over 100 distinct sign languages are severely lacking.
arXiv:2608. 16031v1 Announce Type: new Abstract: Camera-based object detectors are vulnerable to physical adversarial attacks designed to suppress detections.
GRIP (Grounded Reasoning via Information-Restricted Premises) addresses the query dominance problem in retrieval-augmented generation by enforcing a capacity asymmetry: the decoder retains full access to the query while retrieved evidence is funneled through a severe stochastic bottleneck. This design forces the evidence channel to encode only residual information not present in the query. On five reasoning benchmarks, GRIP surpasses strong iterative baselines, reduces query–latent mutual information by about 30×, cuts hallucination by 73%, and its bottleneck outputs occupy subspaces less aligned with the query than baseline representations.
arXiv:2606. 12654v2 Announce Type: replace-cross Abstract: We develop a new, differentially private mean estimator called the balloon mean.
arXiv:2510. 22819v3 Announce Type: replace Abstract: The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it captures the learner's actual decisions and describes the evolution of the learning process over time.
arXiv:2601. 06404v2 Announce Type: replace Abstract: Federated Clustering (FC) faces a critical bottleneck in real-world scenarios, i.
arXiv:2608. 15687v1 Announce Type: new Abstract: Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure.
arXiv:2608. 15815v1 Announce Type: new Abstract: WiFi Channel State Information (CSI) has emerged as a privacy-preserving alternative to cameras for human pose estimation.
arXiv:2608. 15619v1 Announce Type: new Abstract: Emotion recognition from text keeps improving on benchmarks, yet whether an accuracy ceiling has been reached is seldom asked with discipline.