Article | Jiakang Yuanhttps://jiakangyuan.github.io/publication_types/article/ArticleHugoBlox Kit (https://hugoblox.com)en-usTue, 30 Jun 2026 00:00:00 +0000https://jiakangyuan.github.io/media/icon_hu_9c4aa5876d5401cd.pngArticlehttps://jiakangyuan.github.io/publication_types/article/Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agenthttps://jiakangyuan.github.io/publications/agents-a1/Tue, 30 Jun 2026 00:00:00 +0000https://jiakangyuan.github.io/publications/agents-a1/From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulatorhttps://jiakangyuan.github.io/publications/calibrated_rl/Wed, 27 May 2026 00:00:00 +0000https://jiakangyuan.github.io/publications/calibrated_rl/MLG-Stereo: ViT Based Stereo Matching with Multi-Stage Local-Global Enhancementhttps://jiakangyuan.github.io/publications/mle-stereo/Wed, 22 Apr 2026 00:00:00 +0000https://jiakangyuan.github.io/publications/mle-stereo/Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challengeshttps://jiakangyuan.github.io/publications/hacking-survey/Wed, 15 Apr 2026 00:00:00 +0000https://jiakangyuan.github.io/publications/hacking-survey/Intern-S1-Pro: Scientific multimodal foundation model at trillion scalehttps://jiakangyuan.github.io/publications/intern-s1-pro/Sun, 01 Mar 2026 00:00:00 +0000https://jiakangyuan.github.io/publications/intern-s1-pro/InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discoveryhttps://jiakangyuan.github.io/publications/internagent-1-5/Sun, 01 Feb 2026 00:00:00 +0000https://jiakangyuan.github.io/publications/internagent-1-5/LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understandinghttps://jiakangyuan.github.io/publications/lstmmas/Sat, 17 Jan 2026 00:00:00 +0000https://jiakangyuan.github.io/publications/lstmmas/SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligencehttps://jiakangyuan.github.io/publications/scievalkit/Tue, 06 Jan 2026 00:00:00 +0000https://jiakangyuan.github.io/publications/scievalkit/AutoMLGen: Navigating Fine-Grained Optimization for Coding Agentshttps://jiakangyuan.github.io/publications/automlgen/Thu, 09 Oct 2025 00:00:00 +0000https://jiakangyuan.github.io/publications/automlgen/Sequential Token Merging: Revisiting Hidden Stateshttps://jiakangyuan.github.io/publications/sequential-token-merging/Fri, 19 Sep 2025 00:00:00 +0000https://jiakangyuan.github.io/publications/sequential-token-merging/InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verificationhttps://jiakangyuan.github.io/publications/novelseek/Sun, 18 May 2025 00:00:00 +0000https://jiakangyuan.github.io/publications/novelseek/OmniCaptioner: One Captioner to Rule Them Allhttps://jiakangyuan.github.io/publications/omnicaptioner/Wed, 09 Apr 2025 00:00:00 +0000https://jiakangyuan.github.io/publications/omnicaptioner/