A fruitful approach towards understanding generalization in machine learning involves characterizing how models separate generalizable structure from idiosyncratic or even corrupted features of training data. Fisher information has emerged as a diagnostic tool for this separation, leveraging loss geometry to distinguish generalization from memorization. Here we investigate this connection in vision models trained on CIFAR-10 with controlled noise that can be learned only through memorization. We show that projecting model weights onto the top Fisher eigenvectors decouples general task performance from noisy sample memorization, and we investigate how this decoupling presents differentially across layers. We show that the same phenomena are present in small transformers trained to solve a synthetic in-context learning task, and are reproduced in closed form in a simple, analytically solvable linear model. Our results reveal that Fisher information captures aspects of the geometric structure underlying how neural networks allocate capacity between generalization and memorization.
A model may select the correct answer yet fail to construct it through a sequence of local decisions. We introduce Choice2Seq, a diagnostic benchmark that measures correctness retention across complete-answer selection and sequential construction in independent runs on the same problems and candidate sets. Sequence Composition Rate (SCR) measures the fraction of correctly selected items that are also answered correctly through local construction. Jev achieves 97.1% and 99.5% selection accuracy on arithmetic and lexical retrieval, yet retains only 33.0% and 2.1% of those correct choices under serial construction, respectively. Substantial gaps also emerge for StartLux and Qwen, including when Qwen emits characters directly. Restricting local options to candidate-supported characters improves construction, while explicit position indexing improves copying fidelity, even for incorrect selections. These interventions distinguish task correctness, plan fidelity, and output compliance. Matched dialogue-state evaluations reveal that local field construction largely preserves Jev's correct states but reduces Qwen's mean-turn accuracy, highlighting task- and interface-dependent differences. Sequence-level confidence and request-cost analyses further characterize completed outputs.
Spatial transcriptomics jointly captures molecular state, tissue morphology, and spatial organization, yet spatial-domain methods are typically compared only at late training checkpoints, obscuring differences in convergence efficiency. We introduce MP-MNCA, a morphology-prior masked neighbor cross-attention framework that preserves the full 3,000 dimensional highly-variable-gene representation while selectively routing molecular information across spatial neighbors, with histological similarity incorporated as a continuous attention prior under a self-supervised masked neighbor-contrastive objective. Across 12 heterogeneous human dorsolateral prefrontal cortex (DLPFC) sections, MP-MNCA is evaluated against established spatial-domain baselines using both convergence trajectories and epoch-wise spatial-domain visualizations. Our results show that MP-MNCA (i) reaches coherent spatial-domain structure in substantially fewer training epochs, as reflected quantitatively by convergence curves and qualitatively by progressive spatial grids, and (ii) maintains strong clustering quality, achieving a mean peak refined ARI of 0.546 versus 0.549 for the strongest baseline (STAIG), while attaining the highest mean refined NMI of 0.657 versus 0.640. Moreover, MP-MNCA outperforms STAIG on 7 of 12 sections in ARI and 11 of 12 in NMI, demonstrating faster convergence without sacrificing spatial-domain quality.
Time series (TS) anomaly detection (AD) lacks a universal detector, with the best choice determined by the series rather than by the algorithm. Existing methods therefore either select one detector for each series or average a pool of them. However, both assume that no label ever arrives, while a deployed monitor does receive them, since an operator confirms the alarms it raises. In this paper, we propose ONESHOT, which uses a single confirmed anomaly to weight the pool rather than to choose one detector from it. Specifically, we score each detector on the confirmed anomaly, and those scores become the weights of a soft mixture over the whole pool. We show that a single confirmed anomaly is enough to come close to the best detector for the series. Across 152 univariate and 73 multivariate series, ONESHOT outperforms the strongest single detector, averaging the whole pool, and even picking the best detector on the confirmed event. Code is available at: https://github.com/seunghan96/one_shot.
As large language models are increasingly adopted as multi-party communication facilitators, there is a growing demand for agents capable of balancing diverse group dynamics across contexts. However, existing LLM facilitators are often fine-tuned for task-specific objectives; generalized LLM-based facilitation methods that can adapt to different types of tasks and diverse group dynamics are underdeveloped. To address this gap, we present GUIDE (Generalized Unified Intervention for Dynamic Exchanges, a framework for developing generalized LLM-based facilitators across different multi-party contexts. GUIDE evaluates facilitation across both objective task outcomes and subjective metrics, including psychological safety and perceived friction. Within this framework, we study whether LLMs can self-learn generalized facilitation strategy offline to real-time interventions. We first collect multi-party human interactions guided by task-specific expert LLM facilitators (N=432 conversations). We then employ a self-learning method in which an LLM induces an actionable strategic playbook from conversations and iteratively refines it using feedback from an LLM judge aligned with human annotators (N=20), developing a single generalized facilitator that outperforms the three task-specific expert facilitators on held-out conversations 61.4% win rate. Finally, we evaluate these improvements empirically; in a real-time online empirical study, the self-learned generalized facilitator preserves facilitator performance and group productivity, improves speaking comfort and reduces interpersonal friction, while using 24.7% fewer turns and 29.0% fewer words than the expert prompts. These findings provide empirical evidence that LLMs can learn generalizable, task-agnostic social facilitation from task-specific human interactions, on-par with hand-crafted task-specific prompts across diverse group settings.
The Model Context Protocol provides a shared interaction substrate for the agentic web, allowing heterogeneous services to expose capabilities through a standardized interface. Learning to use this ecosystem entails a hierarchy of capabilities: tool-format skills, server-level transfer, and cross-server composition. We present MCPDisCo, an ecosystem-scale reinforcement learning framework for MCP-native agents. Using a Thought-Markov Decision Process (Thought-MDP), the framework explicitly represents internal reasoning alongside routing, execution, and termination and trains on real-server, long-horizon interactions spanning 70 MCP servers and 527 tools across six domains. We study the reasoning--tool seesaw, a joint-learning failure mode in which improvement in one objective can accompany deterioration in the other. To mitigate potential interference, MCPDisCo combines token-masked reward attribution with bidirectional gradient surgery: the former separates direct supervision for reasoning and action spans, while the latter removes conflicting components from both objective gradients in shared parameters. MCPDisCo achieves higher success with fewer chain-of-thought tokens. On the out-of-distribution MCP-Atlas and the GAIA benchmark, MCPDisCo maintains monotone gains, confirming that the learned behavior generalizes beyond the training server distribution and broader agentic tasks. Model weight and implementation are available.
Activation steering has recently been used as a memory for skills: past experiences of an agent are stored as steering vectors and retrieved later. Facts and preferences about the user are assumed to need text instead. We test that assumption with a training-free activation memory beside a frozen LLM. The change an experience causes in late-layer states is stored as a shift, filed under a whitened key for the conversation's gist, and added back in a later session only when the gist matches. We argue that such a shift is a fixed average of an effect that attention, in context, recomputes for every question, so only question-independent content can survive. In a pre-registered study on Qwen3.5-2B and 9B, with judges from four model families, the memory is selective (about 98% of unrelated replies are unchanged), but facts are stored as the word to say, in the last layers only, and are almost never used (at most 15% clean use, against 96-98% in context). Leanings transfer only in a narrow strength window. Most strikingly, the reference subtracted when writing a preference decides whether its concept or its direction survives: unless the opposite is subtracted, a stored dislike is recalled as a like.
Can an autonomous AI agent reverse engineer a binary as well as a skilled human analyst? Do they adopt the same strategy, and can agents scale to real-world programs? We compare human and LLM-based software reverse engineering (SRE): nine models tackle two compact static-analysis challenges previously solved by human analysts, scored with a common understanding rubric, and we record their complete interactions with IDA Pro. This lets us compare not only what humans and agents recover, but also how they investigate a binary. The best agents (GPT-5.5 Pro, Claude Opus 4.8, and Kimi K3) achieve statistically human-competitive understanding on both tasks, while weaker models remain far behind. Ablations show that the gap depends on code representation and workflow demands, not on model capability alone: open-weight models improve substantially with richer code representations, whereas frontier models show no significant change. Similar success rates hide different workflows. Humans repeatedly revisit functions and follow local program structure; strong agents jump across the binary, retrieve information broadly, and rarely return to inspected code, a behavior we call greedy fetching. This strategy is not fixed: given semantically richer code, agents fetch less without losing understanding. Because greedy fetching aggregates large amounts of code in the agent's context, we measure context-window saturation across 4,000 real-world binaries: large windows accommodate many programs, but larger applications and lower-level representations quickly exhaust them. Autonomous reverse engineering is becoming competitive, with a large speed advantage, but scaling it will require better navigation, selective retrieval, and persistent analysis state, not merely larger context windows.
We present a generator of Thai klon pad verse, one stanza from a short topic, and evaluate it against human verse on held-out topics. The generator is a masked language model initialised from WangchanBERTa over a fixed canvas with two layers: a sound layer of pronounced syllables, where rhyme, tone and syllable count are enforced as hard masks, and a word layer of whole words, so that no word is cut into written pieces. Decoding commits one cell at a time and samples at temperature 0.4; one sample is drawn per topic, with no selection, reranking or repair. On 78 held-out topics never used in development, judged by three independent runs of a frozen LLM judge in the same pools as the human stanzas from which the topics were written, 70.5% of the generated stanzas pass form, lexical cleanness of all four lines and topic alignment together, against 76.9% for the human stanzas (difference -6.4 points, 95% CI [-19.2, +6.4]). Cleanness is level with human (85.9% vs. 87.2%), and the stanzas pass form and cleanness together slightly more often than the human ones (+3.8 points, [-6.4, +14.1]); the difference lies in alignment (84.6% vs. 91.0%), on topics that were written from the human stanzas. The low temperature matters: at higher temperatures the same model passes clearly fewer of the same topics, because lexical errors lie in the model's lower-probability choices; sharpening the sampling distribution removes most of them, at a cost in vocabulary (7.5% rare words against 16.5% in the human stanzas) and diversity. The pre-registered target, all-three within 5 points of human, is missed by 1.4 points. KlonSuphap-LM, the only public klon pad generator we know of, passes none of the 78 held-out topics when judged in separate pools together with the method's and the human stanzas (form 19.2%, cleanness 3.8%).
Generative AI makes options cheap and shifts the bottleneck of creative work from generating options to screening them. We argue that AI's value depends on whether its options arrive before or after the team's screen. In our model, early options compete for a place in the portfolio; late options arrive after that competition and are kept unscreened. In a preregistered experiment, we randomly assigned 148 three-person teams to five schedules of access to the same language model during a product-design task with timed search and selection stages. Moving the same 15 minutes of access from search to selection lowered expert-rated creativity by 0.62 standard deviations, although teams used the model at similar rates. Platform logs locate the difference at the screen. Early access enlarged the pool of ideas fivefold, and teams pruned it. Late-access teams reached the screen with the same small pool as teams without AI and then searched again, devoting 29% of their selection-stage queries to generating new options, compared with 11% for teams with access throughout. Late access added breadth, not quality: these teams submitted 73% more proposals than did teams without AI. Language-model judges detected the benefit of access but not the cost of late timing.
Accurate and efficient analysis of dental radiographs has become increasingly important for disease diagnosis and clinical decision making. In particular, dental radiographs segmentation plays a critical role as it is challenging due to several reasons, such as low contrast, noise in the images, variations in the image quality, etc. Previous studies have primarily addressed these challenges using convolutional neural networks (CNN)-based models. However, direct comparison of these segmentation models is still challenging due to the variations among the experimental settings. Therefore, we mainly compared four segmentation models, including Pyramid Scene Parsing Network (PSPNet), DeepLabV3, UNet, and UNet++, through a fair, controlled experimentation setting under varying conditions such as image sizes and batch sizes. For this, we used 1269 dental radiography images, and prior to training, we implemented a series of preprocessing techniques. To assess the models, we used several metrics, including Dice coefficient (DICE), Intersection over Union (IoU), accuracy, precision, training and validation losses. According to our results, UNet++ demonstrated the highest IoU score of 0.6719, and a DICE value of 0.7869, showing superior results in terms of segmentation, specifically when configured with an image size of 300x300 and a batch size of 16. In addition, we also explored the effect of image resolutions and batch sizes on model performance and accuracy under different architectures. Therefore, this study provides insights into the strengths of different segmentation models and the potential of deep learning-based semantic segmentation methods for improving automated dental radiograph analysis.
支持边缘人工智能（AI）推理作为网络服务颇具挑战，因为当前移动系统能够传输张量，却无法暴露或理解赋予这些张量实际运行意义的推理上下文。已有研究通过动态分区、协同推理和分割流水线来弥合这一差距；然而，这些方案仍然受应用约束、对网络无感知或缺乏上下文。本文提出 Inference on Demand（IoD），这是一种按需推理抽象，通过类似 CAMARA 的应用程序接口（API）暴露分割推理，并在 5G 用户面路径中以带内方式传输感知分割的张量上下文。我们在基于可编程用户面功能（UPF）的测试平台上，使用可分区的视觉 AI 工作负载对 IoD 进行了评估，结果表明，自适应分割选择可以作为面向网络的服务运行，同时避免静态配置僵化的成本特征。结合我们的研究结果，当服务意图、运行时分区和张量传输对移动数据平面可见时，分割推理便不再只是卸载。这为网络原生 AI 服务开辟了道路，使可编程电信基础设施能够为面向用户的应用协调计算、上下文和连接。
Adapting to a new world and reasoning correctly about which outcomes are possible under rules one has not met before is a basic capacity underlying general intelligence. We study it in small discrete worlds: sets of grid configurations consistent with a shared set of rules, concretely Sudoku-like puzzles built from a common base and a handful of extra rules. We train a single depth-recurrent model on many combinations of rules and test it at four levels of novelty: a new puzzle, a new combination of known rules, a pairing of rules never seen together, and a rule instance not seen at all during training. The model receives the active rules either as a symbolic description or as two solved examples, and a model that gets no rule information is used as a baseline. At recombining rules it was trained on, the description matches or exceeds examples ($99\%$ against $95\%$ on new combinations). On rule instances whose components never co-occurred in training, the description falls below the no-information baseline while examples stay above it. The framework allows us to test many such generalization regimes in more systematic way than benchmarks such as ARC-AGI and provides new ground for evaluating depth-recurrent reasoning models, which are typically tested on saturated Sudoku benchmarks.
Quantization plays a crucial role in efficiently deploying deep learning models on resource-constrained devices. Post-training quantization does not require access to the original dataset or retraining the full model. Current methods that achieve high performance close to baseline results typically require INT8 fixed-point integers. However, achieving higher model compression with lower bit-widths often leads to significant performance degradation. In this paper, we propose VLCQ, a post-training quantization method that relaxes the fixed-point encoding constraint, enabling more flexible exploration of quantization techniques through variable-length encoding. This approach achieves competitive or improved performance while reducing bit-widths, without requiring access to training data or model fine-tuning. Extensive experiments on image classification, segmentation, and object detection demonstrate that VLCQ improves model compression and accuracy compared with state-of-the-art post-training quantization approaches. For per-channel quantization, VLCQ surpasses FP32 accuracy and Piece-Wise Linear Quantization (PWLQ) on most evaluated models, achieving up to 6x compression compared with FP32 and up to 1.7x compared with PWLQ. When prioritizing compression with limited accuracy loss, VLCQ achieves up to 12.25x compression compared with FP32 with less than 4% performance degradation. For per-tensor quantization, VLCQ is competitive with Data-Free Quantization (DFQ), while providing greater flexibility to achieve lower bit rates across different tasks and models.
Chain-of-thought prompting enables reasoning in large language models but produces explanations that are difficult to verify, expensive to generate, and not always faithful. We introduce a Structural Chain-of-Thought framework where models generate executable computational graphs instead of free-form reasoning. The final answer is obtained by deterministically executing the graph. The model is trained using graph-based reinforcement learning that rewards structural validity, answer correctness, and node overlap with reference graphs. Experiments across five benchmarks and four model families show that our method consistently improves accuracy over supervised graph training and can reduce generation length by up to 5-6x compared with standard GRPO and chain-of-thought supervised training. Our faithfulness experiments reveal that models trained with our approach tend to rely on deriving their answers from the generated graphs rather than producing post-hoc rationalizations as usually in chain-of-thought reasoning.
Small AI models may be just months away from spreading on their own across poorly secured consumer devices like smart TVs and robot vacuums, according to a new Anthropic study. In tests, one model already completed the full infection chain. CEO Dario Amodei has warned that a swarm like this could take over the entire internet with a persistent botnet within 6 to 12 months, causing hundreds of billions of dollars in damage. The article Anthropic study warns that small AI models could soon replicate across everyday devices appeared first on The Decoder .
Microsoft researchers found that autonomous AI agents get trapped in what they call "idea basins" because of their growing chat context, local solution regions they can't escape. Their "Fork-and-Flush" method clears the chat history but keeps the workspace, achieving up to 66 percent better results on the same compute budget. The article Clearing chat history helps AI agents find better solutions appeared first on The Decoder .
Google Deepmind's AlphaProof Nexus solved dozens of open math problems, including nine Erdős problems two of which were unsolved for 56 years, per a study in Science. The publication comes as OpenAI faces a boycott for dumping AI proofs on GitHub without peer review. Deepmind had its results reviewed before publishing. The article Google Deepmind's AlphaProof Nexus solved dozens of open math problems and actually got peer reviewed appeared first on The Decoder .