FY
Fangcong Yin
cs.CLcs.AIcs.LGcs.CVcs.IRstat.ML
On Valency
published · living versionsW_5yrdmwj8·v1 · currentpublished
Self-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling
with Ming Yin, Tanvi Bhandarkar, Aashu Singh, Eryk Helenowski +5
1 version
W_a4rf6d2y·v1published
Preprints & journals
16 papers in the corpus · 2024–2026Self-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling2610.28388v1 · Fangcong Yin, Ming Yin, Tanvi Bhandarkar et al.2026 · 0 citationsarXivon Valency
Assertion and Belief: Moore's Paradox in Language Models2610.25586v1 · Anshun Asher Zheng, Weili Cao, Fangcong Yin et al.2026 · 0 citationsarXivon Valency
When History Misleads: Asymmetric Margin Supervision for Instruction-Guided LLM Generative Recommendation2610.02600v1 · Ming Yin, Yuhan Yang, Chen Chen et al.2026 · 0 citationsarXiv
When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs2608.03506v1 · Omatharv Bharat Vaidya, Connor Thomas Jerzak, Zayne Rea Sprague et al.2026 · 0 citationsarXiv
Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning2607.02490v1 · Liyan Tang, Fangcong Yin, Greg Durrett2026 · 0 citationsarXiv
Randomized YaRN Improves Length Generalization for Long-Context Reasoning2606.23687v3 · Manas Mehta, Fangcong Yin, Greg Durrett2026 · 0 citationsarXiv
Detecting and Suppressing Reward Hacking with Gradient Fingerprints2604.16242v2 · Songtao Wang, Quang Hieu Pham, Fangcong Yin et al.2026 · 0 citationsarXiv
DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models2602.22175v2 · Xi Ye, Wuwei Zhang, Fangcong Yin et al.2026 · 0 citationsarXiv
Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking2506.09944v2 · Wuwei Zhang, Fangcong Yin, Howard Yen et al.2025 · 1 citationarXiv
Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models2506.00653v3 · Femi Bello, Anubrata Das, Fanzhi Zeng et al.2025 · 0 citationsarXiv
Learning Composable Chains-of-Thought2505.22635v2 · Fangcong Yin, Zeyu Leo Liu, Liu Leqi et al.2025 · 0 citationsarXiv
ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models2505.13444v3 · Liyan Tang, Grace Kim, Xinyu Zhao et al.2025 · 4 citationsarXiv
LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation2501.05414v3 · Xi Ye, Fangcong Yin, Yinghui He et al.2025 · 1 citationarXiv
Understanding Synthetic Context Extension via Retrieval Heads2410.22316v4 · Xinyu Zhao, Fangcong Yin, Greg Durrett2024 · 1 citationarXiv
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning2409.12183v3 · Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez et al.2024 · 13 citationsarXiv
LoFiT: Localized Fine-tuning on LLM Representations2406.01563v2 · Fangcong Yin, Xi Ye, Greg Durrett2024 · 5 citationsarXiv
Career total: 16 works. 16 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.