Reward Bench 2
Collection
Datasets, spaces, and models for Reward Bench 2 benchmark and paper!
•
11 items
•
Updated
•
11
Kunal Suri
suryakiran786
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
6 days ago
Reward Bench 2
upvoted
a
paper
18 days ago
BizFinBench: A Business-Driven Real-World Financial Benchmark for
Evaluating LLMs
upvoted
an
article
29 days ago
TinyAgents: A Minimal Experiment with Code Agents and MCP Tools
Organizations
suryakiran786's activity
upvoted
a
collection
6 days ago
upvoted
a
paper
18 days ago
upvoted
an
article
29 days ago
Article
TinyAgents: A Minimal Experiment with Code Agents and MCP Tools
By
•
•
29
reacted to
Kseniase's
post with 👀
3 months ago
Post
2065
9 Multimodal Chain-of-Thought methods
How Chain-of-Thought (CoT) prompting can unlock models' full potential across images, video, audio and more? Finding special multimodal CoT techniques is the answer.
Here are 9 methods of Multimodal Chain-of-Thought (MCoT). Most of them are open-source:
1. KAM-CoT -> KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning (2401.12863)
This lightweight framework combines CoT prompting with knowledge graphs (KGs) and achieves 93.87% accuracy
2. Multimodal Visualization-of-Thought (MVoT) -> Imagine while Reasoning in Space: Multimodal Visualization-of-Thought (2501.07542)
Lets models generate visual reasoning traces, using a token discrepancy loss to improve visual quality
3. Compositional CoT (CCoT) -> Compositional Chain-of-Thought Prompting for Large Multimodal Models (2311.17076)
Uses scene graph (SG) representations generated by the LMM itself to improve performance on compositional and general multimodal benchmarks
4. URSA -> URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics (2501.04686)
Brings System 2-style thinking to multimodal math reasoning, using a 3-module CoT data synthesis process with CoT distillation, trajectory-format rewriting and format unification
5. MM-Verify -> MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification (2502.13383)
Introduces a verification mechanism with MM-Verifier and MM-Reasoner that implements synthesized high-quality CoT data for multimodal reasoning
6. Duty-Distinct CoT (DDCoT) -> DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models (2310.16436)
Divides the reasoning responsibilities between LMs and visual models, integrating the visual recognition capabilities into the joint reasoning process
7. Multimodal-CoT from Amazon Web Services -> Multimodal Chain-of-Thought Reasoning in Language Models (2302.00923)
A two-stage framework separates rationale generation from answer prediction, allowing the model to reason more effectively using multimodal inputs
8. Graph-of-Thought (GoT) -> Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Large Language Models (2305.16582)
This two-stage framework models reasoning as a graph of interconnected ideas, improving performance on text-only and multimodal tasks
More in the comments👇
How Chain-of-Thought (CoT) prompting can unlock models' full potential across images, video, audio and more? Finding special multimodal CoT techniques is the answer.
Here are 9 methods of Multimodal Chain-of-Thought (MCoT). Most of them are open-source:
1. KAM-CoT -> KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning (2401.12863)
This lightweight framework combines CoT prompting with knowledge graphs (KGs) and achieves 93.87% accuracy
2. Multimodal Visualization-of-Thought (MVoT) -> Imagine while Reasoning in Space: Multimodal Visualization-of-Thought (2501.07542)
Lets models generate visual reasoning traces, using a token discrepancy loss to improve visual quality
3. Compositional CoT (CCoT) -> Compositional Chain-of-Thought Prompting for Large Multimodal Models (2311.17076)
Uses scene graph (SG) representations generated by the LMM itself to improve performance on compositional and general multimodal benchmarks
4. URSA -> URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics (2501.04686)
Brings System 2-style thinking to multimodal math reasoning, using a 3-module CoT data synthesis process with CoT distillation, trajectory-format rewriting and format unification
5. MM-Verify -> MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification (2502.13383)
Introduces a verification mechanism with MM-Verifier and MM-Reasoner that implements synthesized high-quality CoT data for multimodal reasoning
6. Duty-Distinct CoT (DDCoT) -> DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models (2310.16436)
Divides the reasoning responsibilities between LMs and visual models, integrating the visual recognition capabilities into the joint reasoning process
7. Multimodal-CoT from Amazon Web Services -> Multimodal Chain-of-Thought Reasoning in Language Models (2302.00923)
A two-stage framework separates rationale generation from answer prediction, allowing the model to reason more effectively using multimodal inputs
8. Graph-of-Thought (GoT) -> Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Large Language Models (2305.16582)
This two-stage framework models reasoning as a graph of interconnected ideas, improving performance on text-only and multimodal tasks
More in the comments👇
- 1 reply
upvoted
4
papers
3 months ago
SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?
Paper
•
2503.12349
•
Published
•
41
API Agents vs. GUI Agents: Divergence and Convergence
Paper
•
2503.11069
•
Published
•
37
TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools
Paper
•
2503.10970
•
Published
•
17
PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
Paper
•
2502.16111
•
Published
•
9
liked
a
Space
4 months ago
upvoted
a
paper
4 months ago
liked
a
Space
4 months ago
upvoted
an
article
4 months ago
Article
NPHardEval Leaderboard: Unveiling the Reasoning Abilities of Large Language Models through Complexity Classes and Dynamic Updates
By
and 3 others
•
•
4
liked
a
dataset
4 months ago
upvoted
an
article
4 months ago
Article
Agent Leaderboard: Evaluating AI Agents in Multi-Domain Scenarios
By
and 1 other
•
•
22
upvoted
4
papers
4 months ago
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper
•
2502.06703
•
Published
•
153
Efficient Tool Use with Chain-of-Abstraction Reasoning
Paper
•
2401.17464
•
Published
•
21
Training Language Model Agents without Modifying Language Models
Paper
•
2402.11359
•
Published
•
2
Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments
Paper
•
2402.14672
•
Published
•
1
reacted to
Kseniase's
post with 🔥
4 months ago
Post
7929
8 New Types of RAG
RAG techniques continuously evolve to enhance LLM response accuracy by retrieving relevant external data during generation. To keep up with current AI trends, new RAG types incorporate deep step-by-step reasoning, tree search, citations, multimodality and other effective techniques.
Here's a list of 8 latest RAG advancements:
1. DeepRAG -> DeepRAG: Thinking to Retrieval Step by Step for Large Language Models (2502.01142)
Models retrieval-augmented reasoning as a Markov Decision Process, enabling strategic retrieval. It dynamically decides when to retrieve external knowledge and when rely on parametric reasoning.
2. RealRAG -> RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning (2502.00848)
Enhances novel object generation by retrieving real-world images and using self-reflective contrastive learning to fill knowledge gap, improve realism and reduce distortions.
3. Chain-of-Retrieval Augmented Generation (CoRAG) -> Chain-of-Retrieval Augmented Generation (2501.14342)
Retrieves information step-by-step and adjusts it, also deciding how much compute power to use at test time. If needed it reformulates queries.
4. VideoRAG -> VideoRAG: Retrieval-Augmented Generation over Video Corpus (2501.05874)
Enables unlimited-length video processing, using dual-channel architecture that integrates graph-based textual grounding and multi-modal context encoding.
5. CFT-RAG -> CFT-RAG: An Entity Tree Based Retrieval Augmented Generation Algorithm With Cuckoo Filter (2501.15098)
A tree-RAG acceleration method uses an improved Cuckoo Filter to optimize entity localization, enabling faster retrieval.
6. Contextualized Graph RAG (CG-RAG) -> CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs (2501.15067)
Uses Lexical-Semantic Graph Retrieval (LeSeGR) to integrate sparse and dense signals within graph structure and capture citation relationships
7. GFM-RAG -> GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation (2502.01113)
A graph foundation model that uses a graph neural network to refine query-knowledge connections
8. URAG -> URAG: Implementing a Unified Hybrid RAG for Precise Answers in University Admission Chatbots -- A Case Study at HCMUT (2501.16276)
A hybrid system combining rule-based and RAG methods to improve lightweight LLMs for educational chatbots
RAG techniques continuously evolve to enhance LLM response accuracy by retrieving relevant external data during generation. To keep up with current AI trends, new RAG types incorporate deep step-by-step reasoning, tree search, citations, multimodality and other effective techniques.
Here's a list of 8 latest RAG advancements:
1. DeepRAG -> DeepRAG: Thinking to Retrieval Step by Step for Large Language Models (2502.01142)
Models retrieval-augmented reasoning as a Markov Decision Process, enabling strategic retrieval. It dynamically decides when to retrieve external knowledge and when rely on parametric reasoning.
2. RealRAG -> RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning (2502.00848)
Enhances novel object generation by retrieving real-world images and using self-reflective contrastive learning to fill knowledge gap, improve realism and reduce distortions.
3. Chain-of-Retrieval Augmented Generation (CoRAG) -> Chain-of-Retrieval Augmented Generation (2501.14342)
Retrieves information step-by-step and adjusts it, also deciding how much compute power to use at test time. If needed it reformulates queries.
4. VideoRAG -> VideoRAG: Retrieval-Augmented Generation over Video Corpus (2501.05874)
Enables unlimited-length video processing, using dual-channel architecture that integrates graph-based textual grounding and multi-modal context encoding.
5. CFT-RAG -> CFT-RAG: An Entity Tree Based Retrieval Augmented Generation Algorithm With Cuckoo Filter (2501.15098)
A tree-RAG acceleration method uses an improved Cuckoo Filter to optimize entity localization, enabling faster retrieval.
6. Contextualized Graph RAG (CG-RAG) -> CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs (2501.15067)
Uses Lexical-Semantic Graph Retrieval (LeSeGR) to integrate sparse and dense signals within graph structure and capture citation relationships
7. GFM-RAG -> GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation (2502.01113)
A graph foundation model that uses a graph neural network to refine query-knowledge connections
8. URAG -> URAG: Implementing a Unified Hybrid RAG for Precise Answers in University Admission Chatbots -- A Case Study at HCMUT (2501.16276)
A hybrid system combining rule-based and RAG methods to improve lightweight LLMs for educational chatbots
-
- 1 reply
liked
a
dataset
4 months ago