PaperHub

Mohit Bansal

~Mohit_Bansal2

46
论文总数
23.0
年均投稿
5.8
平均评分
接收情况34/46
会议分布
ICLR
30
COLM
8
NeurIPS
7
ICML
1

发表论文 (46 篇)

202528 篇

6.8
5

CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion

ICLR 2025Poster
5.3
4

RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives

ICLR 2025Rejected
6.0
4

See It from My Perspective: How Language Affects Cultural Bias in Image Understanding

ICLR 2025Poster
5.3
4

LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits

ICLR 2025Rejected
7.0
3

LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits

NeurIPS 2025Poster
6.5
4

Adapt-$\infty$: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection

ICLR 2025Poster
7.5
4

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback

ICLR 2025Spotlight
7.0
4

Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

ICLR 2025Oral
6.3
4

Retrieval-Augmented Generation with Conflicting Evidence

COLM 2025Poster
7.0
4

Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression

COLM 2025Poster
6.0
4

Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

NeurIPS 2025Poster
5.7
3

Learning to Generate Unit Tests for Automated Debugging

COLM 2025Poster
5.7
3

GenerationPrograms: Fine-grained Attribution with Executable Programs

COLM 2025Poster
4.8
5

MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning

ICLR 2025Rejected
6.0
3

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation

ICLR 2025Poster
6.0
4

QAPyramid: Fine-grained Evaluation of Content Selection for Text Summarization

COLM 2025Poster
5.3
3

What Matters for Model Merging at Scale?

ICLR 2025Rejected
6.0
5

VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning

ICLR 2025Poster
4.0
4

Glider: Global and Local Instruction-Driven Expert Router

ICLR 2025withdrawn
3.8
4

System 1.x: Learning to Balance Fast and Slow Planning with Language Models

ICLR 2025Poster
6.1
4

Self-Consistency Preference Optimization

ICML 2025Poster
6.8
4

ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding

NeurIPS 2025Poster
4.6
5

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

ICLR 2025withdrawn
6.0
2

Unbounded: A Generative Infinite Game of Character Life Simulation

ICLR 2025Poster
5.0
4

Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level

ICLR 2025withdrawn
6.5
4

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel

ICLR 2025Poster
6.0
4

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

NeurIPS 2025Poster
6.5
4

Anyprefer: An Agentic Framework for Preference Data Synthesis

ICLR 2025Poster

202418 篇

5.6
5

$\mathbb{D}^2$ Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning

ICLR 2024Poster
7.5
4

Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks

ICLR 2024Spotlight
6.5
4

LACIE: Listener-Aware Finetuning for Calibration in Large Language Models

NeurIPS 2024Poster
4.6
5

Multimodal Representation Learning by Alternating Unimodal Adaptation

ICLR 2024withdrawn
6.0
3

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models

ICLR 2024Poster
5.5
4

ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models

ICLR 2024Poster
6.0
4

ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs

ICLR 2024Rejected
4.0
4

VideoDirectorGPT: Consistent Multi-Scene Video Generation via LLM-Guided Planning

ICLR 2024withdrawn
5.6
5

VideoDirectorGPT: Consistent Multi-Scene Video Generation via LLM-Guided Planning

COLM 2024Poster
6.3
4

DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning

COLM 2024Poster
2.5
4

Efficient Low-Rank Diffusion Model Training for Text-to-Image Generation

ICLR 2024withdrawn
5.3
4

Dynamic Adapter Merging for Continual Video Question-Answering Learning

ICLR 2024Rejected
6.3
3

EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents

COLM 2024Poster
6.3
4

SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data

NeurIPS 2024Poster
6.3
3

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy

ICLR 2024Spotlight
6.0
3

Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation

ICLR 2024Poster
6.0
4

GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations

NeurIPS 2024Poster
6.3
4

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

ICLR 2024Poster
合作者 (20)