Causal Transformer language models suffer from strictly sequential decoding and a quadratic per-step attention cost, resulting in expensive inference and an inability to revise previous tokens during text generation. While linear-time causal models and discrete diffusion models each address these weaknesses, their integration remains inherently inconsistent and underdeveloped. In this work, we propose B3D-RWKV, a diffusion-based RWKV variant that integrates the model’s 𝒪(L) inference efficiency with parallel, bidirectional discrete-diffusion through a triplet-block layout method. B3D-RWKV-7.2B reaches comparable accuracy on an 8-task suite versus existing models while significantly outperforming baselines in decoding throughput with an average of 1.6× speedup. Code is available at https://github.com/leonardodalinky/B3D-RWKV.

Recent interest in multimodal large language models (MLLMs) raises a central question: can they reason over dynamic visual evidence rather than merely recognize objects or events in individual frames? This ability, which we refer to as *video temporal-logical reasoning*, requires models to maintain, update, and compose evidence as visual states evolve across frames. Existing video benchmarks often conflate this capability with scene complexity, static recognition, or uncontrolled temporal variation. To isolate this capability, we introduce Video-MME-Logical, a controlled benchmark organized around five temporal-logical operations: state tracking, sequential counting, temporal ordering, dynamic spatiality, and structural composition. The benchmark contains 25 fine-grained task categories generated with controlled object states, transitions, temporal dependencies, and logical compositions. It enables difficulty-controlled final-answer evaluation by varying temporal horizon and reasoning complexity, and supports intermediate-state diagnostics by verifying whether models recover the required logical reasoning trace before producing the final answer. Experiments with state-of-the-art MLLMs reveal a substantial human-model gap, especially as temporal-logical complexity increases. Supervised fine-tuning on up to 500K generated samples improves performance but remains insufficient to close the reasoning gap, positioning Video-MME-Logical as a scalable testbed for analyzing and improving temporal-logical reasoning in MLLMs.

We propose an efficient method to generate white-box adversarial examples to trick a character-level neural classifier. We find that only a few manipulations are needed to greatly decrease the accuracy. Our method relies on an atomic flip operation, which swaps one token for another, based on the gradients of the one-hot input vectors. Due to efficiency of our method, we can perform adversarial training which makes the model more robust to attacks at test time. With the use of a few semantics-preserving constraints, we demonstrate that HotFlip can be adapted to attack a word-level classifier as well.