Papers30

#Chain-of-Thought

SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs

Jintao Tong, Shilin Yan et al.Feb 5arXiv

SwimBird is a multimodal AI that can switch how it thinks: only in text, only in vision (with hidden picture-like thoughts), or a mix of both.

#SwimBird#switchable reasoning#hybrid autoregressive

BABE: Biology Arena BEnchmark

Intermediate

Junting Zhou, Jin Chen et al.Feb 5arXiv

BABE is a new benchmark that tests if AI can read real biology papers and reason from experiments like a scientist, not just recall facts.

#BABE Benchmark#Experimental Reasoning#Causal Reasoning

Reinforced Attention Learning

Intermediate

Bangzheng Li, Jianmo Ni et al.Feb 4arXiv

This paper teaches AI to pay attention better by training its focus, not just its words.

#Reinforced Attention Learning#attention policy#multimodal LLM

Privileged Information Distillation for Language Models

Intermediate

Emiliano Penaloza, Dheeraj Vattikonda et al.Feb 4arXiv

The paper shows how to train a language model with special extra hints (privileged information) during practice so it can still do well later without any hints.

#Privileged Information#Knowledge Distillation#π-Distill

No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding

Intermediate

Vynska Amalia Permadi, Xingwei Tan et al.Feb 3arXiv

This paper builds ID-MoCQA, a new two-step (multi-hop) quiz set about Indonesian culture that makes AI connect clues before answering.

#multi-hop question answering#cultural reasoning#Indonesian culture

ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought

Intermediate

Fanmeng Wang, Haotian Liu et al.Jan 30arXiv

Chain-of-Thought (CoT) makes AI think step by step, but it is slow because it writes many tokens one by one.

#Chain-of-Thought#Latent Reasoning#Variational Auto-Encoder

Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning

Intermediate

Yifan Wang, Shiyu Li et al.Jan 21arXiv

Render-of-Thought (RoT) turns the model’s step-by-step thinking from long text into slim images so the model can think faster with fewer tokens.

#Render-of-Thought#Chain-of-Thought#Latent Reasoning

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

Intermediate

Haocheng Xi, Charlie Ruan et al.Jan 20arXiv

Reinforcement learning (RL) for large language models is slow because the rollout (text generation) stage can take more than 70% of training time, especially for long, step-by-step answers.

#FP8 quantization#on-policy reinforcement learning#precision flow

FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation

Intermediate

Jing Zuo, Lingzhou Mu et al.Jan 20arXiv

FantasyVLN teaches a robot to follow language instructions while looking around, using a smart, step-by-step thinking style during training but not at test time.

#Vision-and-Language Navigation#Chain-of-Thought#Multimodal CoT

Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders

Intermediate

Siqi Kou, Jiachun Jin et al.Jan 15arXiv

Most text-to-image models act like word-to-pixel copy machines and miss the hidden meaning in our prompts.

#think-then-generate#reasoning-aware text-to-image#LLM encoder

PRL: Process Reward Learning Improves LLMs' Reasoning Ability and Broadens the Reasoning Boundary

Intermediate

Jiarui Yao, Ruida Wang et al.Jan 15arXiv

Large language models usually get only a final thumbs-up or thumbs-down at the end of their answer, which is too late to fix mistakes made in the middle.

#Process Reward Learning#PRL#Reasoning LLMs

Patient-Similarity Cohort Reasoning in Clinical Text-to-SQL

Intermediate

Yifei Shen, Yilun Zhao et al.Jan 14arXiv

This paper introduces CLINSQL, a 633-task benchmark that turns real clinician-style questions into SQL challenges over the MIMIC-IV v3.1 hospital database.

#clinical text-to-SQL#EHR#MIMIC-IV

1 2 3