TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
hub Mixed citations
Mimo-vl technical report
Mixed citation behavior. Most common role is background (57%).
18
Pith papers citing it
Background
57% of classified citations
hub tools
citation-role summary
background 4
baseline 3
citation-polarity summary
representative citing papers
EVE enables verifiable self-evolution of MLLMs by using a Challenger-Solver architecture to generate dynamic executable visual transformations that produce VQA problems with absolute execution-verified ground truth.
rDPO uses offline-built rubrics to generate on-policy preference data for DPO, raising benchmark scores in visual tasks over outcome-based filtering and style baselines.
VISTA-Bench shows vision-language models degrade on visualized text in images compared to equivalent pure text, with larger gaps under increased perceptual difficulty.
Video-OPD uses on-policy distillation from a frontier teacher to turn sparse episode rewards into dense step-wise signals for more efficient post-training of MLLMs on temporal video grounding.
MLLMs know event timing during prefill via sparse Temporal Grounding Heads but lose it in autoregressive decoding; restricting visual context to the high-attention interval at inference time improves VTG performance on three benchmarks.
Introduces VURB benchmark and VUP-35K dataset to train discriminative and generative video reward models that achieve SOTA performance on VURB and VideoRewardBench.
DiffCap-Bench supplies a diverse IDC benchmark with ten categories and LLM judging grounded in human difference lists to evaluate MLLMs more robustly than prior lexical metrics.
OMIBench benchmark reveals that current LVLMs achieve at most 50% on Olympiad problems requiring reasoning across multiple images.
SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.
MiMo-Embodied is a single foundation model that achieves state-of-the-art results on 17 embodied AI benchmarks and 12 autonomous driving benchmarks through multi-stage learning, curated data, and CoT/RL fine-tuning that produces positive cross-domain transfer.
PEER applies GRPO reinforcement learning with a unified process-outcome reward model to structured empathetic reasoning steps on the SER dataset, yielding gains in empathy, strategy alignment, and human-likeness.
F2G improves video temporal grounding accuracy by decoupling event identification from boundary measurement using predictive temporal perception to create citable evidence segments for LLM reasoning.
Rebalancing designer-painter roles by assigning design to the understanding module via the new DIM dataset yields SOTA image editing performance with a 4.6B model.
JoyAI-Image unifies visual understanding and generation via an MLLM-MMDiT architecture with spatial training signals to reach competitive benchmark performance and stronger spatial intelligence.
The book introduces the origins, mathematical setup, and optimization stages of RLHF including reward modeling, reinforcement learning, rejection sampling, and direct alignment algorithms.
citing papers explorer
-
TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos
TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
-
EVE: Verifiable Self-Evolution of MLLMs via Executable Visual Transformations
EVE enables verifiable self-evolution of MLLMs by using a Challenger-Solver architecture to generate dynamic executable visual transformations that produce VQA problems with absolute execution-verified ground truth.
-
Visual Preference Optimization with Rubric Rewards
rDPO uses offline-built rubrics to generate on-policy preference data for DPO, raising benchmark scores in visual tasks over outcome-based filtering and style baselines.
-
VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?
VISTA-Bench shows vision-language models degrade on visualized text in images compared to equivalent pure text, with larger gaps under increased perceptual difficulty.
-
Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation
Video-OPD uses on-policy distillation from a frontier teacher to turn sparse episode rewards into dense step-wise signals for more efficient post-training of MLLMs on temporal video grounding.
-
MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues
MLLMs know event timing during prefill via sparse Temporal Grounding Heads but lose it in autoregressive decoding; restricting visual context to the high-attention interval at inference time improves VTG performance on three benchmarks.
-
Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models
Introduces VURB benchmark and VUP-35K dataset to train discriminative and generative video reward models that achieve SOTA performance on VURB and VideoRewardBench.
-
DiffCap-Bench: A Comprehensive, Challenging, Robust Benchmark for Image Difference Captioning
DiffCap-Bench supplies a diverse IDC benchmark with ten categories and LLM judging grounded in human difference lists to evaluate MLLMs more robustly than prior lexical metrics.
-
OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model
OMIBench benchmark reveals that current LVLMs achieve at most 50% on Olympiad problems requiring reasoning across multiple images.
-
SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.
-
MiMo-Embodied: X-Embodied Foundation Model Technical Report
MiMo-Embodied is a single foundation model that achieves state-of-the-art results on 17 embodied AI benchmarks and 12 autonomous driving benchmarks through multi-stage learning, curated data, and CoT/RL fine-tuning that produces positive cross-domain transfer.
-
PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning
PEER applies GRPO reinforcement learning with a unified process-outcome reward model to structured empathetic reasoning steps on the SER dataset, yielding gains in empathy, strategy alignment, and human-likeness.
-
Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding
F2G improves video temporal grounding accuracy by decoupling event identification from boundary measurement using predictive temporal perception to create citable evidence segments for LLM reasoning.
-
Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing
Rebalancing designer-painter roles by assigning design to the understanding module via the new DIM dataset yields SOTA image editing performance with a 4.6B model.
-
JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
JoyAI-Image unifies visual understanding and generation via an MLLM-MMDiT architecture with spatial training signals to reach competitive benchmark performance and stronger spatial intelligence.
-
Reinforcement Learning from Human Feedback
The book introduces the origins, mathematical setup, and optimization stages of RLHF including reward modeling, reinforcement learning, rejection sampling, and direct alignment algorithms.
- Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
- Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation