Non-invasive brain-computer interfaces (BCIs) are beginning to benefit from large, public benchmarks. However, current benchmarks target relatively simple, foundational tasks like Speech Detection and Phoneme Classification, while application-ready results on tasks like Brain-to-Text remain elusive. We propose Keyword Spotting (KWS) as a practically applicable, privacy-aware intermediate task. Using the deep 52-hour, within-subject LibriBrain corpus, we provide standardized train/validation/test splits for reproducible benchmarking, and adopt an evaluation protocol tailored to extreme class imbalance. Concretely, we use area under the precision-recall curve (AUPRC) as a robust evaluation metric, complemented by false alarms per hour (FA/h) at fixed recall to capture user-facing trade-offs. To simplify deployment and further experimentation within the research community, we are releasing an updated version of the pnpl library with word-level dataloaders and Colab-ready tutorials. As an initial reference model, we present a compact 1-D Conv/ResNet baseline with focal loss and top-k pooling that is trainable on a single consumer-class GPU. The reference model achieves approximately 13x the permutation baseline AUPRC on held-out sessions, demonstrating the viability of the task. Exploratory analyses reveal: (i) predictable within-subject scaling - performance improves log-linearly with more training hours - and (ii) the existence of word-level factors (frequency and duration) that systematically modulate detectability.

Embodied agents are expected to perform object navigation in dynamic, open-world environments. However, existing approaches typically rely on static trajectories and a fixed set of object categories during training, overlooking the real-world requirement for continual adaptation to evolving scenarios. To facilitate related studies, we introduce the continual object navigation benchmark, which requires agents to acquire navigation skills for new object categories while avoiding catastrophic forgetting of previously learned knowledge. To tackle this challenge, we propose C-Nav, a continual visual navigation framework that integrates two key innovations: (1) A dual-path anti-forgetting mechanism, which comprises feature distillation that aligns multi-modal inputs into a consistent representation space to ensure representation consistency, and feature replay that retains temporal features within the action decoder to ensure policy consistency. (2) An adaptive sampling strategy that selects diverse and informative experiences, thereby reducing redundancy and minimizing memory overhead. Extensive experiments across multiple model architectures demonstrate that C-Nav consistently outperforms existing approaches, achieving superior performance even compared to baselines with full trajectory retention, while significantly lowering memory requirements. The code will be publicly available at https://bigtree765.github.io/C-Nav-project.

From these personas, we synthetically construct comprehensive world models that encode: Workplace hierarchy and relationship context Work patterns and communication styles Available action space A with corresponding parameter spaces P Pain points and operational constraints For instance, given a senior account manager with 20 years of client-facing experience as shown in figure 2, the world model might identify "client documentation upkeep" as a pain point, while also modeling specific client relationships and their respective engagement contexts. Bottleneck Generation: Using the contextualized world model, we generate bottleneck b: a persona-relevant, actionable user-need that satisfies our formal definition (see Section 2). Each bottleneck b is designed to be identifiable through evidence T in the document set D and resolvable through exactly one action a A. User Datastore: For each sample S, we construct the document set D = T K. The True positives T - documents where f(d) = 1 - collectively provide sufficient evidence to identify bottleneck b. Distractors K are documents where f(d) = 0, introducing realistic noise with respect to the bottleneck. In our current datastore setup, all the generated documents are either emails, calendar events, or text documents, as exemplified in Figures 1 and 2. To mirror real-world complexity, we employ two key design principles: (i) Evidence distribution: We often distribute evidence for b across multiple documents in T, requiring agents to synthesize information from t different sources.

Machine unlearning seeks to selectively remove the "influence" of specific training data on a model's outputs. The ideal goal is Retrain Equivalence--behavior identical to a model trained from scratch on only the retained data. This goal was formulated for models trained on i.i.d. data batches, but modern pipelines often involve multi-stage training, with each stage having a distinct data distribution and objective. Examples include LLM fine-tuning for alignment, reasoning ability, etc. Our study shows via theory and experiments that this shift to multi-stage training introduces a fundamental barrier for machine unlearning. The theory indicates that the outcome of local unlearning--methods that only use gradients computed on the forget set--is path-dependent. That is, a model's behavior during unlearning is influenced by the order of its training stages during learning, making it impossible for path-oblivious algorithms to universally achieve Retrain Equivalence. We empirically demonstrate the same phenomenon in LLM post-training across Llama and Qwen models (1B to 14B) with gradient ascent, NPO, and SimNPO local unlearning algorithms. Models fine-tuned via different orderings of identical training stages diverge in behavior during unlearning, with the degradation in GSM8K accuracy after unlearning varying by over 20% across paths. We also observe that some learning paths consistently produce models that unlearn slowly. During unlearning, whether the probability mass gets squeezed into paraphrasing or alternative concepts is also path-dependent. These results consistently show that Retrain Equivalence is an ill-posed target for local unlearning algorithms, so long as the target models are trained in stages. In situations where access to models' training histories is hard, the current work calls for rethinking the definition and desiderata of machine unlearning.

With the increasing ubiquity of AR/VR devices, the deployment of deep learning models on edge devices has become a critical challenge. These devices require real-time inference, low power consumption, and minimal latency. Many framework designers face the conundrum of balancing efficiency and performance. We design a light framework that adopts an encoder-decoder architecture and introduces several key contributions aimed at improving both efficiency and accuracy. We apply sparse convolution on a ResNet-18 backbone to exploit the inherent sparsity in hand pose images, achieving a 42% end-to-end efficiency improvement. Moreover, we propose our SPLite decoder. This new architecture significantly boosts the decoding process's frame rate by 3.1x on the Raspberry Pi 5, while maintaining accuracy on par. To further optimize performance, we apply quantization-aware training, reducing memory usage while preserving accuracy (PA-MPJPE increases only marginally from 9.0 mm to 9.1 mm on FreiHAND). Overall, our system achieves a 2.98x speed-up on a Raspberry Pi 5 CPU (BCM2712 quad-core Arm A76 processor). Our method is also evaluated on compound benchmark datasets, demonstrating comparable accuracy to state-of-the-art approaches while significantly enhancing computational efficiency.

Although Large Language Model (LLM)-based agents are increasingly used in financial trading, it remains unclear whether they can reason and adapt in live markets, as most studies test models instead of agents, cover limited periods and assets, and rely on unverified data. To address these gaps, we introduce Agent Market Arena (AMA), the first lifelong, real-time benchmark for evaluating LLM-based trading agents across multiple markets. AMA integrates verified trading data, expert-checked news, and diverse agent architectures within a unified trading framework, enabling fair and continuous comparison under real conditions. It implements four agents, including InvestorAgent as a single-agent baseline, TradeAgent and HedgeFundAgent with different risk styles, and DeepFundAgent with memory-based reasoning, and evaluates them across GPT-4o, GPT-4.1, Claude-3.5-haiku, Claude-sonnet-4, and Gemini-2.0-flash. Live experiments on both cryptocurrency and stock markets demonstrate that agent frameworks display markedly distinct behavioral patterns, spanning from aggressive risk-taking to conservative decision-making, whereas model backbones contribute less to outcome variation. AMA thus establishes a foundation for rigorous, reproducible, and continuously evolving evaluation of financial reasoning and trading intelligence in LLM-based agents.

Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adapt long prompt templates by forcing the model to generate the initial part of a restricted or harmful response. In this work, we show that existing jailbreak attacks that leverage such mechanisms to unlock the model response can be detected by a straightforward perplexity-based filtering on the input prompt. To overcome this issue, we propose LatentBreak, a white-box jailbreak attack that generates natural adversarial prompts with low perplexity capable of evading such defenses. LatentBreak substitutes words in the input prompt with semantically-equivalent ones, preserving the initial intent of the prompt, instead of adding high-perplexity adversarial suffixes or long templates. These words are chosen by minimizing the distance in the latent space between the representation of the adversarial prompt and that of harmless requests. Our extensive evaluation shows that LatentBreak leads to shorter and low-perplexity prompts, thus outperforming competing jailbreak algorithms against perplexity-based filters on multiple safety-aligned models.

Reinforcement Learning with Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) are the main RL paradigms used in LLM post-training, each offering distinct advantages. However, RLHF struggles with interpretability and reward hacking because it relies on human judgments that usually lack explicit criteria, whereas RLVR is limited in scope by its focus on correctness-based verifiers. We propose Reinforcement Learning with Binary Flexible Feedback (RLBFF), which combines the versatility of human-driven preferences with the precision of rule-based verification, enabling reward models to capture nuanced aspects of response quality beyond mere correctness. RLBFF extracts principles that can be answered in a binary fashion (e.g. accuracy of information: yes, or code readability: no) from natural language feedback. Such principles can then be used to ground Reward Model training as an entailment task (response satisfies or does not satisfy an arbitrary principle). We show that Reward Models trained in this manner can outperform Bradley-Terry models when matched for data and achieve top performance on RM-Bench (86.2%) and JudgeBench (81.4%, #1 on leaderboard as of September 24, 2025). Additionally, users can specify principles of interest at inference time to customize the focus of our reward models, in contrast to Bradley-Terry models. Finally, we present a fully open source recipe (including data) to align Qwen3-32B using RLBFF and our Reward Model, to match or exceed the performance of o3-mini and DeepSeek R1 on general alignment benchmarks of MT-Bench, WildBench, and Arena Hard v2 (at <5% of the inference cost). Models: https://huggingface.co/collections/nvidia/reward-models-10-2025

Complex-valued signals encode both amplitude and phase, yet most deep models treat attention as real-valued correlation, overlooking interference effects. We introduce the Holographic Transformer, a physics-inspired architecture that incorporates wave interference principles into self-attention. Holographic attention modulates interactions by relative phase and coherently superimposes values, ensuring consistency between amplitude and phase. A dual-headed decoder simultaneously reconstructs the input and predicts task outputs, preventing phase collapse when losses prioritize magnitude over phase. We demonstrate that holographic attention implements a discrete interference operator and maintains phase consistency under linear mixing. Experiments on PolSAR image classification and wireless channel prediction show strong performance, achieving high classification accuracy and F1 scores, low regression error, and increased robustness to phase perturbations. These results highlight that enforcing physical consistency in attention leads to generalizable improvements in complex-valued learning and provides a unified, physics-based framework for coherent signal modeling. The code is available at https://github.com/EonHao/Holographic-Transformers.

Uncovering cause-and-effect mechanisms from data is fundamental to scientific progress. While large language models (LLMs) show promise for enhancing causal discovery (CD) from unstructured data, their application to the increasingly prevalent multimodal setting remains a critical challenge. Even with the advent of multimodal LLMs (MLLMs), their efficacy in multimodal CD is hindered by two primary limitations: (1) difficulty in exploring intra- and inter-modal interactions for comprehensive causal variable identification; and (2) insufficiency to handle structural ambiguities with purely observational data. To address these challenges, we propose MLLM-CD, a novel framework for multimodal causal discovery from unstructured data. It consists of three key components: (1) a novel contrastive factor discovery module to identify genuine multimodal factors based on the interactions explored from contrastive sample pairs; (2) a statistical causal structure discovery module to infer causal relationships among discovered factors; and (3) an iterative multimodal counterfactual reasoning module to refine the discovery outcomes iteratively by incorporating the world knowledge and reasoning capabilities of MLLMs. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of the proposed MLLM-CD in revealing genuine factors and causal relationships among them from multimodal unstructured data.