Brun
JM-Brun
AI & ML interests
None yet
Organizations
None yet
Diffusion models
Tool calling
-
Hammer: Robust Function-Calling for On-Device Language Models via Function Masking
Paper • 2410.04587 • Published • 2 -
TaskCraft: Automated Generation of Agentic Tasks
Paper • 2506.10055 • Published • 32 -
Direct Multi-Turn Preference Optimization for Language Agents
Paper • 2406.14868 • Published -
MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
Paper • 2508.20453 • Published • 63
Multimodal
-
Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities
Paper • 2505.02567 • Published • 80 -
OmniGen2: Exploration to Advanced Multimodal Generation
Paper • 2506.18871 • Published • 78 -
UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation
Paper • 2506.17202 • Published • 10 -
ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation
Paper • 2506.18095 • Published • 66
Attribution
LLM-as-a-judge
-
Preference Leakage: A Contamination Problem in LLM-as-a-judge
Paper • 2502.01534 • Published • 40 -
Great Models Think Alike and this Undermines AI Oversight
Paper • 2502.04313 • Published • 33 -
CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives
Paper • 2504.10823 • Published • 15 -
CLEAR: Error Analysis via LLM-as-a-Judge Made Easy
Paper • 2507.18392 • Published • 19
LLM-KG
LLM Architecture
-
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper • 2501.08313 • Published • 301 -
Scalable-Softmax Is Superior for Attention
Paper • 2501.19399 • Published • 24 -
FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation
Paper • 2502.01068 • Published • 18 -
Scaling Embedding Layers in Language Models
Paper • 2502.01637 • Published • 24
World model
LLM Math
-
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Paper • 2501.07301 • Published • 99 -
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
Paper • 2502.03544 • Published • 44 -
FoNE: Precise Single-Token Number Embeddings via Fourier Features
Paper • 2502.09741 • Published • 15 -
SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers
Paper • 2502.20545 • Published • 22
Hallucinations
-
Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
Paper • 2411.14257 • Published • 14 -
Distinguishing Ignorance from Error in LLM Hallucinations
Paper • 2410.22071 • Published -
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations
Paper • 2410.18860 • Published • 11 -
MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Paper • 2410.11779 • Published • 26
RL
Prompt Optimization
Tabular
Agents
-
Agentic Knowledgeable Self-awareness
Paper • 2504.03553 • Published • 27 -
Benchmarking LLMs' Swarm intelligence
Paper • 2505.04364 • Published • 20 -
Multi-Agent System for Comprehensive Soccer Understanding
Paper • 2505.03735 • Published • 25 -
LIMI: Less is More for Agency
Paper • 2509.17567 • Published • 102
SLMs
LLM Training
Research Tool
-
PaSa: An LLM Agent for Comprehensive Academic Paper Search
Paper • 2501.10120 • Published • 53 -
DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs
Paper • 2506.08500 • Published • 7 -
SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks
Paper • 2507.01001 • Published • 47 -
SurveyBench: How Well Can LLM(-Agents) Write Academic Surveys?
Paper • 2510.03120 • Published • 6
LLM Data
Reasonning
-
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
Paper • 2501.09751 • Published • 48 -
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
Paper • 2501.09686 • Published • 41 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 429 -
s1: Simple test-time scaling
Paper • 2501.19393 • Published • 124
Interpretability XAI
-
ReAGent: Towards A Model-agnostic Feature Attribution Method for Generative Language Models
Paper • 2402.00794 • Published • 1 -
Rethinking Interpretability in the Era of Large Language Models
Paper • 2402.01761 • Published • 23 -
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
Paper • 2502.03032 • Published • 60 -
Tell me why: Visual foundation models as self-explainable classifiers
Paper • 2502.19577 • Published • 11
Data Agents
RL
Diffusion models
Prompt Optimization
Tool calling
-
Hammer: Robust Function-Calling for On-Device Language Models via Function Masking
Paper • 2410.04587 • Published • 2 -
TaskCraft: Automated Generation of Agentic Tasks
Paper • 2506.10055 • Published • 32 -
Direct Multi-Turn Preference Optimization for Language Agents
Paper • 2406.14868 • Published -
MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
Paper • 2508.20453 • Published • 63
Tabular
Multimodal
-
Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities
Paper • 2505.02567 • Published • 80 -
OmniGen2: Exploration to Advanced Multimodal Generation
Paper • 2506.18871 • Published • 78 -
UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation
Paper • 2506.17202 • Published • 10 -
ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation
Paper • 2506.18095 • Published • 66
Agents
-
Agentic Knowledgeable Self-awareness
Paper • 2504.03553 • Published • 27 -
Benchmarking LLMs' Swarm intelligence
Paper • 2505.04364 • Published • 20 -
Multi-Agent System for Comprehensive Soccer Understanding
Paper • 2505.03735 • Published • 25 -
LIMI: Less is More for Agency
Paper • 2509.17567 • Published • 102
Attribution
SLMs
LLM-as-a-judge
-
Preference Leakage: A Contamination Problem in LLM-as-a-judge
Paper • 2502.01534 • Published • 40 -
Great Models Think Alike and this Undermines AI Oversight
Paper • 2502.04313 • Published • 33 -
CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives
Paper • 2504.10823 • Published • 15 -
CLEAR: Error Analysis via LLM-as-a-Judge Made Easy
Paper • 2507.18392 • Published • 19
LLM Training
LLM-KG
Research Tool
-
PaSa: An LLM Agent for Comprehensive Academic Paper Search
Paper • 2501.10120 • Published • 53 -
DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs
Paper • 2506.08500 • Published • 7 -
SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks
Paper • 2507.01001 • Published • 47 -
SurveyBench: How Well Can LLM(-Agents) Write Academic Surveys?
Paper • 2510.03120 • Published • 6
LLM Architecture
-
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper • 2501.08313 • Published • 301 -
Scalable-Softmax Is Superior for Attention
Paper • 2501.19399 • Published • 24 -
FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation
Paper • 2502.01068 • Published • 18 -
Scaling Embedding Layers in Language Models
Paper • 2502.01637 • Published • 24
LLM Data
World model
Reasonning
-
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
Paper • 2501.09751 • Published • 48 -
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
Paper • 2501.09686 • Published • 41 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 429 -
s1: Simple test-time scaling
Paper • 2501.19393 • Published • 124
LLM Math
-
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Paper • 2501.07301 • Published • 99 -
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
Paper • 2502.03544 • Published • 44 -
FoNE: Precise Single-Token Number Embeddings via Fourier Features
Paper • 2502.09741 • Published • 15 -
SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers
Paper • 2502.20545 • Published • 22
Interpretability XAI
-
ReAGent: Towards A Model-agnostic Feature Attribution Method for Generative Language Models
Paper • 2402.00794 • Published • 1 -
Rethinking Interpretability in the Era of Large Language Models
Paper • 2402.01761 • Published • 23 -
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
Paper • 2502.03032 • Published • 60 -
Tell me why: Visual foundation models as self-explainable classifiers
Paper • 2502.19577 • Published • 11
Hallucinations
-
Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
Paper • 2411.14257 • Published • 14 -
Distinguishing Ignorance from Error in LLM Hallucinations
Paper • 2410.22071 • Published -
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations
Paper • 2410.18860 • Published • 11 -
MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Paper • 2410.11779 • Published • 26