3 | Rabimba Karanjaihttp://rabimba.fyi/publication_types/3/3Hugo Blox Builder (https://hugoblox.com)en-usMon, 19 Oct 2026 00:00:00 +0000http://rabimba.fyi/media/icon_hu_6d534efae7b021f2.png3http://rabimba.fyi/publication_types/3/TxnQA: Benchmarking Analytical Reasoning and Evidence Grounding over Transaction Event Sequenceshttp://rabimba.fyi/publication/transactqa/Mon, 19 Oct 2026 00:00:00 +0000http://rabimba.fyi/publication/transactqa/CM-DPO: Constraint-Margin Direct Preference Optimization for LLM Planninghttp://rabimba.fyi/publication/cm-dpo-planning/Tue, 06 Oct 2026 00:00:00 +0000http://rabimba.fyi/publication/cm-dpo-planning/A Picture is Worth a Thousand Tokens: Lossless Multilingual Context Compression via Pictorial Intermediate Representationshttp://rabimba.fyi/publication/picture-thousand-tokens/Thu, 01 Oct 2026 00:00:00 +0000http://rabimba.fyi/publication/picture-thousand-tokens/CoJo-RAG: Conformalized Joint Co-Optimization of Retrieval and Fine-Tuninghttp://rabimba.fyi/publication/cojo-rag/Thu, 01 Oct 2026 00:00:00 +0000http://rabimba.fyi/publication/cojo-rag/Designing the Outside Option: Anchors, Mixed Equilibria, and Welfare in LLM Routing Auctionshttp://rabimba.fyi/publication/outside-option-routing-auctions/Thu, 01 Oct 2026 00:00:00 +0000http://rabimba.fyi/publication/outside-option-routing-auctions/Motivated Chain-of-Thought and Reduced Scrutiny in LLM Judgeshttp://rabimba.fyi/publication/motivated-cot-llm-judges/Thu, 01 Oct 2026 00:00:00 +0000http://rabimba.fyi/publication/motivated-cot-llm-judges/Unanimous but Wrong: Conformity in Multi-Agent LLM Audit Deliberationhttp://rabimba.fyi/publication/unanimous-but-wrong-conformity/Thu, 01 Oct 2026 00:00:00 +0000http://rabimba.fyi/publication/unanimous-but-wrong-conformity/Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injectionhttp://rabimba.fyi/publication/reachability-capability-confinement/Sun, 30 Aug 2026 00:00:00 +0000http://rabimba.fyi/publication/reachability-capability-confinement/Allocation Before Ranking: Decoupled Token Compression for OmniLLMshttp://rabimba.fyi/publication/allocation-before-ranking/Mon, 03 Aug 2026 00:00:00 +0000http://rabimba.fyi/publication/allocation-before-ranking/Rethinking Publication: A Certification Framework for AI-Enabled Researchhttp://rabimba.fyi/publication/rethinking-publication/Thu, 23 Apr 2026 00:00:00 +0000http://rabimba.fyi/publication/rethinking-publication/zkRansomware: Proof-of-Data Recoverability and Multi-round Game Theoretic Modeling of Ransomware Decisionshttp://rabimba.fyi/publication/zkransomware/Sat, 10 Jan 2026 00:00:00 +0000http://rabimba.fyi/publication/zkransomware/Aligning Vision Language Models via anchorhttp://rabimba.fyi/publication/vision-language-models-anchor/Thu, 01 Jan 2026 00:00:00 +0000http://rabimba.fyi/publication/vision-language-models-anchor/Bridging Confidentiality and Reliability: Open-Weight Agents for Legal Reasoninghttp://rabimba.fyi/publication/bridging-confidentiality-reliability/Thu, 01 Jan 2026 00:00:00 +0000http://rabimba.fyi/publication/bridging-confidentiality-reliability/Closing the Cost Gap in Verifier-Guided RL: A Smart Contract Case Studyhttp://rabimba.fyi/publication/closing-cost-gap-rl/Thu, 01 Jan 2026 00:00:00 +0000http://rabimba.fyi/publication/closing-cost-gap-rl/Hype or Hope? Training LLMs on Decentralized GPU Cloudshttp://rabimba.fyi/publication/training-llms-decentralized/Thu, 01 Jan 2026 00:00:00 +0000http://rabimba.fyi/publication/training-llms-decentralized/Profiler: Per-Question Persona Conditioning of Frozen LLMs via Retrieval and Fusion of Synthesized Profileshttp://rabimba.fyi/publication/profiler-persona/Thu, 01 Jan 2026 00:00:00 +0000http://rabimba.fyi/publication/profiler-persona/Rules That Govern: A Per-Property Analysis of Multi-Agent LLM Deliberationhttp://rabimba.fyi/publication/rules-that-govern/Thu, 01 Jan 2026 00:00:00 +0000http://rabimba.fyi/publication/rules-that-govern/VerifyGen-X: Secure Cross-Chain Smart Contract Generation via Scalable Reinforcement Learning from Formal Verification Feedbackhttp://rabimba.fyi/publication/verifygen-x/Thu, 01 Jan 2026 00:00:00 +0000http://rabimba.fyi/publication/verifygen-x/From General Reasoning to Domain Expertise: Uncovering the Limits of Generalization in Large Language Modelshttp://rabimba.fyi/publication/general-reasoning-domain-expertise/Mon, 16 Jun 2025 00:00:00 +0000http://rabimba.fyi/publication/general-reasoning-domain-expertise/Weaving the Cosmos: WASM-Powered Interchain Communication for AI Enabled Smart Contractshttp://rabimba.fyi/publication/weaving-cosmos-wasm-interchain/Mon, 24 Feb 2025 00:00:00 +0000http://rabimba.fyi/publication/weaving-cosmos-wasm-interchain/Generating Move Smart Contracts based on Conceptshttp://rabimba.fyi/publication/conmover-move-concepts/Tue, 17 Dec 2024 00:00:00 +0000http://rabimba.fyi/publication/conmover-move-concepts/Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computinghttp://rabimba.fyi/publication/harnessing-llms-hpc-unit-tests/Sat, 06 Jul 2024 00:00:00 +0000http://rabimba.fyi/publication/harnessing-llms-hpc-unit-tests/LookALike: Human Mimicry based collaborative decision makinghttp://rabimba.fyi/publication/lookalike-human-mimicry/Sat, 16 Mar 2024 00:00:00 +0000http://rabimba.fyi/publication/lookalike-human-mimicry/Cross Chain Bribery Contracts: Majority vs Mighty Minorityhttp://rabimba.fyi/publication/cross-chain-bribery-contracts-majority-vs-mighty-minority/Thu, 08 Jun 2023 00:00:00 +0000http://rabimba.fyi/publication/cross-chain-bribery-contracts-majority-vs-mighty-minority/Targeted Phishing Campaigns using Large Scale Language Modelshttp://rabimba.fyi/publication/targeted-phishing-llms/Fri, 30 Dec 2022 00:00:00 +0000http://rabimba.fyi/publication/targeted-phishing-llms/Fpswap: Fair and Privacy Friendly Swap of Digital Assets on Blockchainhttp://rabimba.fyi/publication/fpswap/Tue, 21 Jun 2022 00:00:00 +0000http://rabimba.fyi/publication/fpswap/