FROG: Full-Resolution Graph Structure Learning for Relational Deep Learning
This paper introduces FROG, a framework that treats relational database schema graph construction as a learnable optimization problem rather than a fixed design choice. The method formulates table role modeling as a learnable component, allowing tables to dynamically serve as nodes or edges in message passing, with functional dependency constraints ensuring semantic consistency. Experiments show FROG outperforms existing relational deep learning approaches and provides insights into how table roles affect downstream prediction tasks.
Related guides (2)
Related events (8)
Positional vs. Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization
Researchers train a decoder-only Transformer (GPT-J) on two structurally equivalent multi-hop reasoning tasks to study how attention heads specialize into positional or symbolic roles during learning. They find that successful task learning correlates with the emergence of 'pure' heads—exclusively positional or symbolic—and provide theoretical constructions showing how single-layer RoPE-based attention realizes these functions geometrically. A novel 'discrepancy' metric formalizes the robustness difference between the two head types, with symbolic mechanisms shown to extrapolate more reliably to longer sequences than positional ones. The findings have implications for understanding length generalization failures in RoPE-based models.
Semantic Triplet Restoration: A Novel Protocol for Hierarchical Table Understanding in Large Language Models
This paper proposes Semantic Triplet Restoration (STR), a table serialization protocol that rewrites each cell as an atomic fact <item path, feature path, value> to make header-cell alignments explicit for LLMs, replacing HTML/Markdown representations. The authors also introduce TripletQL, a query-aware router that selects relevant triplets per question. Evaluated on four Chinese and English table-QA benchmarks, STR matches or outperforms HTML-based baselines while reducing input token count. Benefits are most pronounced for smaller models and longer tables, suggesting value under constrained inference budgets.
GraphPO: Graph-based Policy Optimization reduces redundancy in LLM reasoning RL
GraphPO is a new reinforcement learning framework that represents reasoning rollouts as directed acyclic graphs rather than independent chains or trees, merging semantically equivalent reasoning paths into equivalence classes to share suffixes and reduce redundant exploration. The approach assigns efficiency advantages to incoming edges and correctness advantages to outgoing edges, deriving process supervision from outcome rewards. Experiments on three LLMs across reasoning and agentic search benchmarks show consistent improvements over chain- and tree-based baselines under equal token or response budgets. The method also provides theoretical guarantees on reduced advantage-estimation variance.
MemDreamer: Hierarchical graph memory and agentic retrieval for long video understanding
MemDreamer is a plug-and-play framework that decouples perception and reasoning for long-video understanding by incrementally building a three-tier Hierarchical Graph Memory capturing spatiotemporal and causal relations. During inference, a reasoning model uses an Observation-Reason-Action loop with agentic tool-augmented retrieval to navigate the memory graph, constraining the context window to 2% of full-context ingestion while achieving a 12.5-point absolute accuracy gain. The system reaches SOTA on four benchmarks, narrowing the gap with human experts to 3.7 points. The authors also report a strong linear correlation between logical reasoning performance and long-video understanding, proposing agentic capability scaling as a new paradigm for multimodal comprehension.
REAL: Reasoning-enhanced temporal graph framework for LLM long-term memory management
REAL is a new framework that represents LLM conversational memory as a temporal, confidence-aware directed property graph, where atomic facts carry validity intervals, confidence scores, and exploration intent labels. It addresses three limitations of prior memory systems: flat text structures, destructive overwrites of evolving facts, and passive retrieval. The system uses non-destructive temporal updates, semantic evaluator-guided hybrid beam search, and counterfactual inference to repair incomplete retrieval states. Experiments show a 22.72% average improvement over flat-text, graph-based, and existing memory baselines.
FFR extends Forward-Forward algorithm to regression tasks with 73% memory reduction
A new arXiv preprint introduces FFR (Forward-Forward for Regression), the first framework to adapt Hinton's Forward-Forward algorithm—a biologically plausible, backpropagation-free training method—to regression problems. FFR introduces an ordinal competitive goodness function, a stratified ladder architecture, and hierarchical prediction with uncertainty estimation to handle continuous target spaces. Across five real-world regression benchmarks, FFR recovers 98.6% of backpropagation accuracy while reducing peak training memory to 27% of BP's at depth 8 and 8% at depth 32, with per-iteration time around 72% of BP's.
VeriTrace: Cognitive-Graph Framework with Explicit Regulatory Loops for Deep Research Agents
VeriTrace introduces a cognitive-graph framework for deep research agents that replaces implicit LLM reasoning over intermediate representations with three explicit regulatory loops: interpretive update, deviation feedback, and schema revision. The system addresses contamination and error propagation in evolving mental models during complex multi-step research tasks. Using Qwen3.5-27B backbones, VeriTrace improves over the strongest matched baseline by 4.22 pp on DeepResearch Bench Insight and 5.9 pp Overall win rate on DeepConsult. With Config-DeepSeek, it achieves the strongest reproducible open-source result on DeepResearch Bench.
Liger GRPO meets TRL: Efficient Reinforcement Learning Training Integration
The Hugging Face blog post announces the integration of Liger Kernel's GRPO (Group Relative Policy Optimization) implementation with TRL (Transformer Reinforcement Learning library). This combination aims to improve memory efficiency and training throughput for RL-based fine-tuning of language models. The integration targets practitioners running GRPO-style training on constrained hardware budgets.