Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607.20818v2 Announce Type: replace-cross Abstract: Many instances of sequential sampling, including audit and inspection scheduling, representative sampling, and treatment assignment, require...
The paper proposes a transparent, user‑configurable rule for selecting arguments in deliberative polls, replacing opaque learned rankers. It formalises argument selection over bipolar justification sets, introduces seven civic recommender criteria, and presents a one‑hop reversed endorsement flow rule that meets them. Experiments on 17,000 simulated runs show the rule performs comparably to random on coverage but outperforms other methods on endorsement mass and robustness under adversarial pressure.
arXiv:2503.17894v3 Announce Type: replace-cross Abstract: We propose generative learner for estimating heterogeneous treatment effects and characterizing the full distribution of causal effects. The...
The paper introduces a two‑layer detector to prevent ‘slopsquatting’—the risk of local coding LLMs fabricating Python package names that adversaries can pre‑register on PyPI. The first layer checks PyPI for existence, while the second uses a Random Forest classifier on ten name‑and‑metadata features; an import reconciler resolves naming mismatches. Embedded in a LangGraph state machine, the system retries at escalating temperatures and falls back to stronger models, achieving hallucination‑free code in 76% of 300 curated prompts and recovering additional runs through intra‑ and cross‑model retries.
arXiv:2505.23462v2 Announce Type: replace Abstract: Blind face restoration from low-quality images is a challenging task that requires not only high-fidelity image reconstruction, but also preservati...
arXiv:2512.23245v3 Announce Type: replace Abstract: Recent text-to-image diffusion models have significantly improved visual quality and text alignment. However, generating a sequence of images while...
arXiv:2504.18346v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have been transformative across many domains. However, hallucination, i.e., confidently outputting incorrect inf...
arXiv:2603.28029v3 Announce Type: replace Abstract: Criticality metrics such as time-to-collision (TTC) quantify collision urgency but do not distinguish the operational consequences of false-positiv...
arXiv:2608.23921v1 Announce Type: new Abstract: Recent Vision-Language Models encode high-resolution images into long visual token sequences, incurring prohibitive prefill costs. To compress them, ex...
Quasar is a new programming language designed to improve large language model (LLM) code actions by separating internal program logic from external tool calls. It allows developers to annotate external calls with effect information and modify internal execution to track these effects, enabling easier implementation of new features. The authors demonstrate Quasar’s utility by adding access control, autoparallelization, and conformal prediction for uncertainty quantification.
arXiv:2606.00930v2 Announce Type: replace-cross Abstract: Mechanistic interpretability routinely reads a probe and labels its top-activating units as the circuit executing the computation. We test th...
arXiv:2604.09057v3 Announce Type: replace Abstract: Audio-video (AV) generation has recently made strong progress in perceptual quality and multimodal coherence, yet generating content with plausible...
arXiv:2603.25507v2 Announce Type: replace-cross Abstract: Network Traffic Classification (NTC) increasingly relies on data-driven models, yet its practical deployment is often constrained by limited...
The paper introduces Variance‑Guided Spatial Attention Fusion (VG‑SAF), a method for robust end‑to‑end driving that fuses camera and LiDAR data while handling asymmetric sensor degradation. VG‑SAF uses a physically grounded augmentor to generate dense reliability masks, modality‑specific experts to predict per‑pixel reliability scales, and a hybrid attention mechanism that gates unreliable cells and balances modalities. The approach also includes a Laplace uncertainty head to signal severe or combined sensor failures, and demonstrates improved closed‑loop robustness on the CARLA Longest6 benchmark across various degradation scenarios.
arXiv:2603.17170v2 Announce Type: replace-cross Abstract: AI agents increasingly execute users' natural-language (NL) tasks by calling Web services, yet today's Web authorizes these calls through OAu...
The paper introduces Evidence-Carrying Termination (ECT), a method that allows tool‑using large language model agents to declare a task complete only when a typed certificate links every required answer claim to valid, in‑scope trace evidence and a deterministic replay confirms the claimed value. In controlled experiments across 48 synthetic tasks and 576 trajectories, ECT eliminated unsafe completions and premature unsupported terminations, outperforming existing termination critics and controllers while maintaining comparable supported completion rates.
arXiv:2608.23984v1 Announce Type: new Abstract: Recent advances in single-image 3D Gaussian head reconstruction have enabled highly realistic and freely renderable digital heads from a single portrai...
The paper "Ghaib in Translation" investigates how large language models (LLMs) handle Urdu, a widely spoken language that is largely absent from safety evaluations. Five prominent LLMs—GPT‑4o, Claude Sonnet 4.5, Gemini 2.5 Flash, Qwen‑2.5, and Llama‑3.1—were tested on six datasets covering Nastaliq Urdu, Roman Urdu, English, and code‑switched Urdu‑English. The study found significant label instability between original‑script and English‑translation classifications, with missed‑in‑Urdu rates ranging from 2.4% to 9.9% (median 4.3%). A review of 205 papers across nine ALW/WOAH editions revealed no dedicated Urdu research, underscoring the language’s neglect in current safety research.
FARCA is a policy‑optimization framework that addresses the problem of noisy factual credit assignment in reinforcement learning for large language models. It transforms coarse factual supervision into token‑level training signals that are both localized and weighted by a reliability estimate derived from counterfactual evidence attribution. Experiments on several factual reasoning benchmarks show that FARCA improves model factuality while maintaining general reasoning abilities.
arXiv:2608.24282v1 Announce Type: new Abstract: Adaptive LiDAR scanning concentrates a limited sensing budget on regions of interest predicted from past object tracks, lowering data volume in autonom...