Recent Posts

Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation

因果思维链 (CausalCoT)：基于上下文隔离阻断全向注意力泄漏

10/23/2026

arxivaics.ai

Direct Pass@k Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning

基于直接 Pass@k 优化的思维前缀剪枝：统合测试期推理的质量与多样性

10/23/2026

arxivaics.ai

LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data

LongZero：无需外部数据，通过自演化任务合成突破 LLM 长上下文推理瓶颈

10/22/2026

arxivaics.cl

Rethinking Video Autoencoders for Interactive World Models

重新思考交互式世界模型的视频自编码器：CADRE 架构与时空压缩权衡

10/22/2026

arxivaics.cv

Adaptive Multi-Token Prediction: How far should we go?

自适应多 Token 预测：投机视界该看多远？

10/21/2026

arxivaics.ai

AEON: Unifying Video and 3D World Models

AEON：融合视频保真度与 3D 几何一致性的通用世界模型

10/21/2026

arxivaics.cv

LatComm: Reusable Context Compression for Latent Communication between Large Language Models

LatComm：大模型间潜空间通信的重用型上下文压缩

10/20/2026

arxivaics.ai

Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy

物理具身递归自进化的能力之源：LLM 具身策略的观测式缩放定律

10/20/2026

arxivaics.ai

Acceptance Is Not Speed: Length Inflation in Training-Free Lossy Speculative Decoding

接收率不等于加速比：有损投机解码中的长度通胀陷阱

10/19/2026

arxivaics.cl

Beyond the Answer: Student-Conditioned Trace Construction for Reasoning Distillation

超越答案监督：基于学生状态条件化轨迹构建的推理蒸馏

10/19/2026

arxivaics.cl

A team of Gemini 4 Argon agents beats Minecraft

Gemini 4 Argon 智能体集群通关《我的世界》：长程自主软件工程的新里程碑

10/16/2026

arxivaics.ai

Designing Transformers for Continuous Diffusion Language Models

为连续扩散大模型重塑 Transformer：LangDiT 架构解析

10/16/2026

arxivaics.ai