Daxin Jiang

MISA-T boosts rollout throughput by over 53% while preserving workload integrity, revolutionizing how RL pipelines manage heterogeneous demands.

TensorCast reveals that decoupling tensor management from computation can boost performance by over 90% in multi-turn interactions, challenging the status quo of LLM infrastructure.

Rethinking GPU reliability, this study shows that ranking nodes by failure risk can outperform traditional predictive maintenance methods, capturing 64% of failures in the top 5% of at-risk GPUs.

Executable vector graphics enable MLLMs to achieve human-like spatial reasoning through a structured visual workspace.

Models may score well on benchmarks but often fail to meet strict perceptual requirements, revealing a hidden brittleness in multimodal evaluations.

Closing the supervision gap in GUI agents boosts success rates from the low-30% range to over 50% through innovative skill-guided learning.

JetSpec shatters the speed ceiling of speculative decoding, achieving up to 9.64x acceleration on complex tasks while maintaining high acceptance rates.

LLM trading agents might seem profitable, but a new benchmark reveals their returns are mostly just riding market trends, not actual stock-picking skill.

Current mobile GUI agents are surprisingly inept at everyday smartphone tasks, achieving only 62% success on a new benchmark of real-world Android apps.

Forget specialized architectures: StepAudio 2.5 proves a single audio-language foundation, shaped by RLHF, can dominate ASR, TTS, and real-time dialogue simultaneously.

Even reward models that get the right answer can be dangerously wrong in their reasoning, leading to worse RLHF outcomes, but R-Align fixes this by explicitly aligning rationales with gold standard judgments.

Forget complex RLHF pipelines: simple PPO with rule-based rewards can outperform state-of-the-art reasoning models while slashing training costs by 90%.