TraFL applies trajectory flow balancing to post-train diffusion language models, preventing mode collapse and delivering consistent gains on reasoning tasks that hold under increased sampling.
Title resolution pending
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
baseline 1
dataset 1
citation-polarity summary
representative citing papers
RelSC is a new graph regression benchmark from program graphs with execution time labels, released in homogeneous (RelSC-H) and multi-relational (RelSC-M) variants to study representation effects.
CAD-Coder generates valid CadQuery scripts from text via supervised fine-tuning followed by reinforcement learning with geometric Chamfer Distance rewards and chain-of-thought planning.
DEX replaces single-depth selection with parallel exploration over multiple candidate depths, committing the final-depth token while collapsing reusable states to reduce per-token computation.
HASP upgrades textual skills into executable Program Functions that intervene in LLM agent loops at inference, post-training, or self-evolution, delivering 25% gains over ReAct and 30.4% over Search-R1 on reasoning benchmarks.
MELT decouples reasoning depth from memory in looped language models by sharing a single gated KV cache per layer and training it via chunk-wise distillation from Ouro starting models.
MAS-Algorithm is a multi-agent workflow that improves AI acceptance rates on algorithmic problems by 6.48% on average, outperforming parameter-efficient fine-tuning.
VILASR integrates visual drawing operations with reasoning in LVLMs via cold-start synthetic training, reflective rejection sampling, and reinforcement learning, yielding an 18.4% average gain on spatial reasoning benchmarks.
LMNet connects stripped pre-trained transformer blocks with trainable seq2seq edges to enable end-to-end differentiable dense-vector communication between language models.
A staged LLM pipeline synthesizes verifiable discrete-event world models from natural language specifications using the DEVS formalism for long-horizon consistency in LLM agents.
TableMaster improves LM table understanding by verbalizing tables with enriched semantics and using adaptive textual-symbolic reasoning, reaching 78.13% accuracy on WikiTQ with GPT-4o-mini.
A survey deriving a unified policy gradient framework for LLM post-training methods and providing technical comparisons of PPO, GRPO, DPO variants.
citing papers explorer
-
Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models
TraFL applies trajectory flow balancing to post-train diffusion language models, preventing mode collapse and delivering consistent gains on reasoning tasks that hold under increased sampling.
-
A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants
RelSC is a new graph regression benchmark from program graphs with execution time labels, released in homogeneous (RelSC-H) and multi-relational (RelSC-M) variants to study representation effects.
-
CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
CAD-Coder generates valid CadQuery scripts from text via supervised fine-tuning followed by reinforcement learning with geometric Chamfer Distance rewards and chain-of-thought planning.
-
Depth Exploration for LLM Decoding
DEX replaces single-depth selection with parallel exploration over multiple candidate depths, committing the final-depth token while collapsing reusable states to reduce per-token computation.
-
Harnessing LLM Agents with Skill Programs
HASP upgrades textual skills into executable Program Functions that intervene in LLM agent loops at inference, post-training, or self-evolution, delivering 25% gains over ReAct and 30.4% over Search-R1 on reasoning benchmarks.
-
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
MELT decouples reasoning depth from memory in looped language models by sharing a single gated KV cache per layer and training it via chunk-wise distillation from Ouro starting models.
-
MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System
MAS-Algorithm is a multi-agent workflow that improves AI acceptance rates on algorithmic problems by 6.48% on average, outperforming parameter-efficient fine-tuning.
-
Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
VILASR integrates visual drawing operations with reasoning in LVLMs via cold-start synthetic training, reflective rejection sampling, and reinforcement learning, yielding an 18.4% average gain on spatial reasoning benchmarks.
-
Language Model Networks: Supervision-Efficient Learning through Dense Communication
LMNet connects stripped pre-trained transformer blocks with trainable seq2seq edges to enable end-to-end differentiable dense-vector communication between language models.
-
Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism
A staged LLM pipeline synthesizes verifiable discrete-event world models from natural language specifications using the DEVS formalism for long-horizon consistency in LLM agents.
-
TableMaster: A Recipe to Advance Table Understanding with Language Models
TableMaster improves LM table understanding by verbalizing tables with enriched semantics and using adaptive textual-symbolic reasoning, reaching 78.13% accuracy on WikiTQ with GPT-4o-mini.
-
Reinforcement Learning for LLM Post-Training: A Survey
A survey deriving a unified policy gradient framework for LLM post-training methods and providing technical comparisons of PPO, GRPO, DPO variants.