Reflect-R1 introduces the first evidence-driven self-correction framework for long video understanding using a three-stage pipeline, stage-decoupled RL via SD-GRPO, and a 120K dataset to achieve SOTA on VideoMME and LongVideoBench.
hub
Advances in neural information processing systems35, 24824–24837 (2022)
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
representative citing papers
A planner-orchestrator system learns long-horizon image editing by maximizing outcome-based rewards from a vision-language judge and refining plans from successful trajectories.
LLM-Foraging uses off-the-shelf LLMs for decentralized tactical decisions in CPFA-based swarm foraging, collecting more resources than GA-tuned baselines across 36 varied configurations while showing greater consistency.
SciEval is a new benchmark of expert-annotated K-12 science lessons for LLM-based automatic evaluation, where zero-shot models perform poorly but fine-tuning yields up to 11% gains.
RESP uses reference-guided sequential prompting with VLMs to improve frame-level and video-level visual glitch detection in games by establishing per-video baselines.
TAIHRI is the first task-aware VLM for close-range HRI that localizes metric-scale 3D coordinates of critical keypoints by quantizing space and performing 2D keypoint reasoning via next-token prediction.
ReShift is a reasoning-level backdoor framework for VLMs that uses poisoned data construction and joint optimization to shift CoT trajectories on trigger while preserving surface coherence.
SEAR introduces a dual-process agentic framework for image restoration that combines pruning-aware MCTS planning with self-evolving episodic memory to address greedy search and episodic amnesia limitations.
Introduces CORTEX benchmark supplying 76,177 validated four-stage diagnostic reasoning traces for open/closed VQA and report generation on chest CT to enable traceable MLLM supervision and evaluation.
Introduces Zoom-then-Diagnose paradigm and uncertainty-aware reward in GRPO for confidence-aware ultrasound VQA, reporting 39.3% improvement in lesion localization across liver, breast, and thyroid datasets.
A trajectory-aware process reward using DTW on sentence embeddings, combined with exact-match in GRPO after SFT, raises mean medical VQA accuracy from 0.598 to 0.689 across six benchmarks.
FinKG-News constructs news-centric financial knowledge graphs to support in-context learning for credit risk report generation across three dimensions, claiming 19-34% quality gains and fewer hallucinations than baselines.
SLAP is a new batch-aware pruning framework that uses distribution-aware stratified sampling and Hessian-approximated gradients to select data, claiming 20-40% less data while matching or exceeding full-dataset performance on LLM instruction tuning tasks.
UniMesh unifies 3D mesh generation and understanding in one model via a Mesh Head interface, Chain of Mesh iterative editing, and an Actor-Evaluator self-reflection loop.
Subagent architectures deliver stable high-throughput optimization under tight time limits while agent teams enable deeper refactoring at the cost of higher fragility.
LC-RAG augments standard RAG by incorporating environment logs to contextualize student discourse, yielding better retrieval and more relevant guidance from the Copa agent in the C2STEM modeling environment.
MedSynapse-V proposes a latent memory evolution framework with meta-query prior retrieval, causal counterfactual refinement via RL, and intrinsic memory transition to improve diagnostic accuracy over chain-of-thought baselines in medical VLMs.
citing papers explorer
-
Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding
Reflect-R1 introduces the first evidence-driven self-correction framework for long video understanding using a three-stage pipeline, stage-decoupled RL via SD-GRPO, and a 120K dataset to achieve SOTA on VideoMME and LongVideoBench.
-
From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing
A planner-orchestrator system learns long-horizon image editing by maximizing outcome-based rewards from a vision-language judge and refining plans from successful trajectories.
-
LLM-Foraging: Large Language Models for Decentralized Swarm Robot Foraging
LLM-Foraging uses off-the-shelf LLMs for decentralized tactical decisions in CPFA-based swarm foraging, collecting more resources than GA-tuned baselines across 36 varied configurations while showing greater consistency.
-
SciEval: A Benchmark for Automatic Evaluation of K-12 Science Instructional Materials
SciEval is a new benchmark of expert-annotated K-12 science lessons for LLM-based automatic evaluation, where zero-shot models perform poorly but fine-tuning yields up to 11% gains.
-
RESP: Reference-guided Sequential Prompting for Visual Glitch Detection in Video Games
RESP uses reference-guided sequential prompting with VLMs to improve frame-level and video-level visual glitch detection in games by establishing per-video baselines.
-
TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction
TAIHRI is the first task-aware VLM for close-range HRI that localizes metric-scale 3D coordinates of critical keypoints by quantizing space and performing 2D keypoint reasoning via next-token prediction.
-
ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language Models
ReShift is a reasoning-level backdoor framework for VLMs that uses poisoned data construction and joint optimization to shift CoT trajectories on trigger while preserving surface coherence.
-
Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution
SEAR introduces a dual-process agentic framework for image restoration that combines pruning-aware MCTS planning with self-evolving episodic memory to address greedy search and episodic amnesia limitations.
-
CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs
Introduces CORTEX benchmark supplying 76,177 validated four-stage diagnostic reasoning traces for open/closed VQA and report generation on chest CT to enable traceable MLLM supervision and evaluation.
-
Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming
Introduces Zoom-then-Diagnose paradigm and uncertainty-aware reward in GRPO for confidence-aware ultrasound VQA, reporting 39.3% improvement in lesion localization across liver, breast, and thyroid datasets.
-
Improving Medical VQA through Trajectory-Aware Process Supervision
A trajectory-aware process reward using DTW on sentence embeddings, combined with exact-match in GRPO after SFT, raises mean medical VQA accuracy from 0.598 to 0.689 across six benchmarks.
-
Evidence-Supported Credit Risk Report Generation Using News-Centric Financial Knowledge Graphs
FinKG-News constructs news-centric financial knowledge graphs to support in-context learning for credit risk report generation across three dimensions, claiming 19-34% quality gains and fewer hallucinations than baselines.
-
SLAP: Stratified Loss-based Pruning for On-Policy Data-Efficient Instruction Tuning
SLAP is a new batch-aware pruning framework that uses distribution-aware stratified sampling and Hessian-approximated gradients to select data, claiming 20-40% less data while matching or exceeding full-dataset performance on LLM instruction tuning tasks.
-
UniMesh: Unifying 3D Mesh Understanding and Generation
UniMesh unifies 3D mesh generation and understanding in one model via a Mesh Head interface, Chain of Mesh iterative editing, and an Actor-Evaluator self-reflection loop.
-
An Empirical Study of Multi-Agent Collaboration for Automated Research
Subagent architectures deliver stable high-throughput optimization under tight time limits while agent teams enable deeper refactoring at the cost of higher fragility.
-
Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval-Augmented Generation (RAG)
LC-RAG augments standard RAG by incorporating environment logs to contextualize student discourse, yielding better retrieval and more relevant guidance from the Copa agent in the C2STEM modeling environment.
-
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
MedSynapse-V proposes a latent memory evolution framework with meta-query prior retrieval, causal counterfactual refinement via RL, and intrinsic memory transition to improve diagnostic accuracy over chain-of-thought baselines in medical VLMs.