arXiv:2603.00045v3 Announce Type: replace Abstract: Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the ``factorization barrier'': the assumption that simultaneously…
arXiv:2604.15699v2 Announce Type: replace Abstract: Graph self-supervised learning can reduce the need for labeled graph data and has been widely used in recommendation, social networks, and…
arXiv:2507.07247v2 Announce Type: replace-cross Abstract: As large language models (LLMs) and visual language models (VLMs) grow in scale and application, attention mechanisms have become a central…
arXiv:2607.16675v1 Announce Type: new Abstract: A point prediction that is well calibrated on average can still be systematically biased conditional on its own value, undermining its…
arXiv:2603.13065v2 Announce Type: replace-cross Abstract: Deep learning models achieve high accuracy in time series classification, yet understanding their class-level decision behaviour remains challenging. Explanations for time…
arXiv:2607.16205v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has emerged as a standard approach for enhancing reasoning in large language models, which typically optimizes…
arXiv:2607.16673v1 Announce Type: new Abstract: Linear-attention models replace the growing KV cache with recurrent states, but autoregressive decoding still reads, updates, and writes these states one…
arXiv:2607.16808v1 Announce Type: new Abstract: Event Argument Extraction (EAE) converts documents into structured event records by identifying argument spans and assigning them schema-defined roles. Document-level EAE…
arXiv:2602.23204v4 Announce Type: replace Abstract: Event cameras report asynchronously per-pixel brightness changes with microsecond latency, encoding dynamic visual information as a sparse stream of events. However,…
arXiv:2607.16232v1 Announce Type: new Abstract: The growing use of statistical learning algorithms to infer human preferences from high-dimensional choice data runs up against a fundamental challenge:…
arXiv:2607.16237v1 Announce Type: new Abstract: Recursive reasoning models solve hard puzzles by applying compact, weight-tied blocks over many refinement steps. Because these blocks are reused many…
arXiv:2607.17398v1 Announce Type: cross Abstract: Analytical placers rely on differentiable objective functions to guide placement, typically combining intermediate surrogate metrics such as half-perimeter wirelength (HPWL) and…
arXiv:2607.16612v1 Announce Type: new Abstract: Backpropagation makes training deep networks memory intensive because it must store intermediate activations. Forward-mode methods avoid this cost, but their gradient…
Real-time multimodal applications, including voice agents and interactive video generation, compose heterogeneous models into pipelines whose efficient deployment requires application-specific decisions about placement, streaming, and intra-model…
Pruning long context for coding agents has been a vital technology for efficient context management. While existing context pruning methods such as SWE-Pruner realize this by…
Scaling robust driving policies is fundamentally bottlenecked by the scarcity of edge cases in curated datasets. While the real world continuously captures these critical events, such…
We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales. Trained with a unified spatio-temporal and physically grounded framework, RynnBrain…
Entropy control has become an effective tool in reinforcement learning (RL) of large language models (LLMs), helping balance exploration-exploitation trade-off during alignment process. Such RL paradigm…
Reinforcement learning (RL) on open-ended tasks compresses an LLM's rubric-based evaluation into a scalar reward, discarding rich textual feedback and conflating responses with distinct quality profiles.…
Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories. However, collecting such data at scale typically requires fully implemented environments with executable…
The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration. This perspective casts the model as an exact estimator, neglecting…
The post-training of Vision-Language-Action (VLA) models is essential due to the diversity of simulators, robot embodiments, and task objectives. Existing compute services, whether offered as direct…
Existing 3D generative models predominantly rely on implicit volumetric representations, which enforce watertight topology and struggle to represent thin-shell and non-manifold geometries such as garments. Geometry…
Serial verification gates are a core reliability primitive in LLM harnesses: a candidate answer is returned only if k verifier calls all accept it. Under conditionally…