3,698 items tracked: 33 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2510.15476v4 Announce Type: replace-cross Abstract: Prompt-security claims for large language models (LLMs) are often compared as properties of individual attacks or defenses, although measured harmfulness depends…
arXiv:2510.24469v2 Announce Type: replace-cross Abstract: Personalized text generation requires models not only to produce coherent text but also to align with a target user's style, tone, and topical focus.
arXiv:2511.00198v2 Announce Type: replace-cross Abstract: Autoregressive language models are usually trained with next-token prediction under a fixed left-to-right target order.
arXiv:2511.01061v2 Announce Type: replace-cross Abstract: Backpropagation (BP) powers modern deep learning, but it must hold every activation in memory until a global backward sweep consumes it, and that sweep locks each…
arXiv:2511.07923v3 Announce Type: replace-cross Abstract: Accurate segmentation of marine organisms is vital for biodiversity monitoring and ecological assessment, yet existing datasets and models remain largely limited…
arXiv:2511.13714v2 Announce Type: replace-cross Abstract: The Segment Anything Model (SAM) family has become a widely adopted vision foundation model, but its ability to control segmentation granularity remains limited.
arXiv:2511.21752v3 Announce Type: replace-cross Abstract: Prompt injection can cause large language models (LLMs) to deviate from their intended tasks by following instructions embedded in untrusted input.
arXiv:2512.21326v3 Announce Type: replace-cross Abstract: Applying well-established statistical methods effectively to LLM evals requires consideration of model correlations and prediction noises.
arXiv:2512.23994v5 Announce Type: replace-cross Abstract: Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling.
arXiv:2601.02978v3 Announce Type: replace-cross Abstract: Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models (LLMs).
arXiv:2601.03321v5 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have substantially advanced Radiology Report Generation (RRG), yet aligning them through reinforcement learning (RL) rema…
arXiv:2601.06157v2 Announce Type: replace-cross Abstract: Alignment in large language models (LLMs) is still largely static: after training, the policy is frozen.
arXiv:2601.07718v2 Announce Type: replace-cross Abstract: Achieving robust humanoid locomotion in complex, unstructured environments requires transitioning from reactive proprioception to proactive perception.
arXiv:2601.11618v4 Announce Type: replace-cross Abstract: An operation's input-output function does not, by itself, determine its computational role within a represented process.
arXiv:2601.12243v3 Announce Type: replace-cross Abstract: Video summarization transforms long videos into concise representations that are easier to document and analyze, especially in high-stakes domains such as surgica…
arXiv:2601.14628v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models inherit powerful semantic representations from large language models, but carrying over their design priorities can leave the…
arXiv:2601.17226v3 Announce Type: replace-cross Abstract: Counterfactual storytelling exposes LLM shortcomings in causal reasoning, where few-shot prompting and SFT fail to produce logical and rational narratives.
arXiv:2601.19618v3 Announce Type: replace-cross Abstract: Differential privacy limits how much each training image can influence a medical imaging model but lowers its diagnostic accuracy.
arXiv:2601.20055v3 Announce Type: replace-cross Abstract: Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental challenge.
arXiv:2601.21590v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) post-training is a dominant approach for improving the reasoning performance of large language models (LLMs), yet growing evidence sug…
arXiv:2601.22725v5 Announce Type: replace-cross Abstract: Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent…
arXiv:2602.00628v3 Announce Type: replace-cross Abstract: We investigate the extent to which an LLM's hidden-state geometry can be recovered from its behavior in psycholinguistic experiments.
arXiv:2602.01433v3 Announce Type: replace-cross Abstract: Multivariate time series in domains such as finance, climate science, and healthcare often exhibit long-term trends, seasonal patterns, and short-term fluctuation…
arXiv:2602.02331v2 Announce Type: replace-cross Abstract: Achieving highly dynamic parkour with humanoid robots on complex terrains unseen during the pre-training stage remains a challenge in robotics.
arXiv:2602.04692v3 Announce Type: replace-cross Abstract: Referring Multi-Object Tracking (RMOT) aims to track specific targets based on language descriptions, playing a vital role in interactive AI systems such as robot…
arXiv:2602.15042v2 Announce Type: replace-cross Abstract: Reliable sleep staging remains challenging for lightweight wearable devices such as single-channel electroencephalography (scEEG) or photoplethysmography (PPG).
arXiv:2602.16356v2 Announce Type: replace-cross Abstract: Semantic scene understanding has enabled robots to reason and perform affordance-driven object interaction.
arXiv:2602.21189v3 Announce Type: replace-cross Abstract: Pass@$k$ is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-answer reason…
arXiv:2603.01786v2 Announce Type: replace-cross Abstract: In this paper, we present a novel learning framework for finding shortest paths in graphs utilizing Generative Flow Networks (GFlowNets).
arXiv:2603.02022v3 Announce Type: replace-cross Abstract: Speech Bandwidth Extension improves clarity and intelligibility by restoring/inferring appropriate high-frequency content for low-bandwidth speech.
arXiv:2603.06135v3 Announce Type: replace-cross Abstract: Distinguishing legitimate critical speech from coordinated conspiracy narratives is a pressing challenge for the integrity of the online information ecosystem, ye…
arXiv:2603.06760v2 Announce Type: replace-cross Abstract: Control co-design jointly optimizes a robot's physical design and its controller.
arXiv:2603.07373v2 Announce Type: replace-cross Abstract: The rapid growth of AI training has dramatically increased datacenter traffic demand and energy consumption, which has motivated renewed interest in optical circu…
arXiv:2603.14371v3 Announce Type: replace-cross Abstract: Embodied AI agents increasingly require parallel execution of multiple tasks, such as manipulation, conversation, and memory construction, from shared observation…
arXiv:2603.16157v2 Announce Type: replace-cross Abstract: While Reinforcement Learning (RL) enhances Large Language Model reasoning, on-policy algorithms like GRPO are sample-inefficient as they discard past rollouts.
arXiv:2603.23356v2 Announce Type: replace-cross Abstract: We propose a novel clustering approach for point-cloud segmentation based on supervised contrastive metric learning (CML).
arXiv:2603.25063v2 Announce Type: replace-cross Abstract: Recent agentic systems demonstrate that large language models can generate complex codebases from natural language prompts.
arXiv:2604.00280v3 Announce Type: replace-cross Abstract: Formal specifications play a central role in ensuring software reliability, yet automatically synthesizing high-quality specifications remains difficult and often…
arXiv:2604.02341v2 Announce Type: replace-cross Abstract: Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers can be checke…
arXiv:2604.04690v3 Announce Type: replace-cross Abstract: Bin picking in real industrial environments remains challenging due to severe clutter, occlusions, and the high cost of traditional 3D sensing setups.
arXiv:2604.06138v2 Announce Type: replace-cross Abstract: Long-context audio reasoning is underserved in both training data and evaluation.
arXiv:2604.07457v2 Announce Type: replace-cross Abstract: While decoupled control schemes for legged mobile manipulators have shown robustness, learning holistic whole-body control policies for tracking global end-effect…
arXiv:2604.12113v2 Announce Type: replace-cross Abstract: Visual Foundation Models (VFMs) such as the Segment Anything Model (SAM) have significantly advanced broad use of image segmentation.
arXiv:2604.18607v2 Announce Type: replace-cross Abstract: LLM-driven program evolution can discover high-quality programs, but high API cost and run-to-run variance hinder reliable progress.
arXiv:2604.19851v2 Announce Type: replace-cross Abstract: Computational social choice studies how conflicting individual preferences are aggregated into a collective decision, with applications to elections, AI evaluatio…
arXiv:2604.22046v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have recently shown strong potential for generating project-level unit tests.
arXiv:2604.22117v3 Announce Type: replace-cross Abstract: Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a subtle but consequential…
arXiv:2604.22560v2 Announce Type: replace-cross Abstract: Graph Visual Question Answering (GVQA) for autonomous driving organizes reasoning into ordered stages, namely Perception, Prediction, and Planning, where planning…
arXiv:2605.00557v2 Announce Type: replace-cross Abstract: Scientific discovery is an extended process of ideation -- surveying prior work, forming hypotheses, and refining reasoning -- yet existing LLM research agents tr…
arXiv:2605.02608v3 Announce Type: replace-cross Abstract: Transformer-based models achieve state-of-the-art dependency parsing for high-resource languages, yet their advantage over simpler architectures in low-resource s…